CGI 2025: 42ND COMPUTER GRAPHICS INTERNATIONAL 2025

This page contains an index consisting of author-provided keywords.

2
2.5D Fine-tuning Framework	ZAP-2.5DSAM: Zero Additional Parameters Advancing 2.5D SAM Adaptation to 3D Tumor Segmentation
2D floorplan segmentation	Exploring Structural Lines for Interior Floorplan Segmentation
2D Signed Distance Field	Single Image Shadow Removal using 2D Signed Distance Field
3
3D animation	A Privacy-preserving Collaborative 3D Design Framework for Copyright Protection
3D cadastre	Self-Adaptive Geometric Updating Method for 3D Cadastral Parcels Based on Geometric Algebra
3D Clothed Human Reconstruction	Enhancing Single-View 3D Clothed Human Reconstruction with Hybrid Prior Integration
3D Craniomaxillofacial Model	Attention-enhanced 3D craniomaxillofacial anatomical landmark detection based on projection
3D Design	Curvilinear Coordinate Systems for 3D Design
3D Editing	Feature Replacement in Gaussian Splatting for 3D Stylization
3D face modeling	Te3DFR: Texture-enabled 3D Face Reconstruction from Monocular Image via Self-supervised Learning
3D fish body	Generating 3D fish motion skeleton via iterative optimization method and FishSkeletonNet
3D Gaussian Splatting	OSH-Splat: Optimizable Semantic Hyperplanes for Enhanced 3D Language Feature Gaussian Splatting Building 3DGS Representation for Single Interested Object via Joint Segmentation-training Framework MC-Gaussian: 3D Gaussian Splatting with Multi-camera in Autonomous Driving
3D Graphics and Vision	3D Reconstructions from Unoriented Points: Recent Advances and Emerging Trends
3D human generation	Text-driven High-quality 3D Human Generation via Variational Gradient Estimationl and Latent Reward Models
3D Human Pose Estimation	Multi-Agent Learning with Hierarchical Prompt for Efficient 3D Human Pose Estimation in Virtual Reality Interpretable Two-Stage Action Quality Assessment via 3D Human Pose Estimation and Dynamic Feature Alignment
3D human reconstruction	UMan: Multi-Scale Feature Reconstruction and Super-Resolution for Single-Image 3D Human Modeling
3D Ken Burns	Instance-guided Cartoon Editing with a Curated Large-scale Dataset
3D Neuron Reconstruction	Efficient Modeling of Long-Range Morphology for 3D Neuron Reconstruction from Electron Microscopy Images
3D pointcloud semantic segmentation	Efficient selective labeling strategies for enhanced few-shot 3D point cloud semantic segmentation
3D Reconstruction	GenericAvatar: Generic Human Modeling from Monocular Video Based on Mesh-guided Gaussians Submodular-based View Selection for Low-Quality Points Rendering with Multi-Feature Point-based NeRF
3D Reconstructions	3D Reconstructions from Unoriented Points: Recent Advances and Emerging Trends
3D Registration	Symbolically Optimized Characteristic Multivector Rotor Estimation for 3D Point Cloud Registration
3D Scene	RelieFormer:End-to-End Bas Relief Generation via Transformer
3d scene reconstruction	Robust bi-level optimization for monocular human and scene reconstruction
3D scene understanding	OSH-Splat: Optimizable Semantic Hyperplanes for Enhanced 3D Language Feature Gaussian Splatting
3D Shape Analysis	Attention-Guided Self-Supervised Distinctive Region Detection in Point Clouds
3D Shape Generation	RelieFormer:End-to-End Bas Relief Generation via Transformer
A
AC Circuit Theory	Keynote: Geometric Algebra in Electrical Engineering: A Comprehensive Review of Power Systems Applications
Action Quality Assessment	Interpretable Two-Stage Action Quality Assessment via 3D Human Pose Estimation and Dynamic Feature Alignment
Action Recognition	Dual-Path Spatio-Temporal Mamba for Skeleton-Based Action Recognition Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions Learning Human-Object Interactions in Videos with Optical Flow
Adaptive Cross-Fusion	Bimodal VIT Adaptive Cross-Fusion Micro-Expression Recognition Based on ECG-QRS Waves
Adaptive Sampling	Adaptive Sampling for Interactive Simulation of Granular Material
Adaptive self-attention mechanism	Multi-Scale Attention and Adaptive Self-Attention for Occlusion-Aware Depth Estimation in Light Field
Adaptive Topology Transformation	Dual-Path Spatio-Temporal Mamba for Skeleton-Based Action Recognition
adaptive training sample selection	TADT: Task-aligned Deep Tracking
Adolescent idiopathic scoliosis	Graph Convolutional Networks for 3D Skeleton-Based Scoliosis Screening Using Gait Sequences
Adversarial attack	Veiled Diffusion: A Diffusion-Based Anti-Customization Adversarial Attack Method via Semantic Misalignment and Low-Frequency Information
Adversarial Example	Enhancing the Transferability of Adversarial Examples against No-Reference Image Quality Assessment Models
Adversarial examples	Malicious Manipulation of Incident Light: Enabling Adversarial Relighting Attack with Physical Interpretability
adversarial makeup transfer	Recognize Me If You Can: Two-stream Adversarial Transfer for Facial Privacy Protection using Fine-grained Makeup
Age Transformation	SelfAge: Personalized Facial Age Transformation Using Self-reference Images
AI agent	MAS-KCL: Knowledge Component Graph Structure Learning with Large Language Model-based Agentic Workflow
AI robots	From Sci-Fi to Reality: Exploring Teenagers' Perceptions and Ideas of AI Robots
AI-generated art · Neural creativity ·	MindCanvas: A Human-Centric Approach to AI-Driven Artistic Creation Through Brain Signals
AI-Generated Content	Towards Culturally Aware AI: Quantified Evaluation of Relevance and Similarity in AI-Generated Images
AIoT	Deep Learning-based Digital Twin for Real-time Fire Safety Management
Air Pollutant	Poll-Sketcher: Visual Exploration of Time-Varying Air Pollutant Data Based on Hand-drawn Sketches
Algebraic Vision	GeloVec: Higher Dimensional Geometric Smoothing for Coherent Visual Feature Extraction in Image Segmentation
AMdown	YOLO-Pest A Model Design for Crop Pest Detection
Analysis · Foundation model · Semantic Segmentation ·	Boosting Remote Semantic Segmentation Using Vision-and- language Foundation Model
anchor-free tracker	ViT-BF: Vision Transformer with Border-aware Features for Visual Tracking
Animation	Extending Implicit Density Projection for Multiphase Fluids
Anisotropic reflectance model	HumanIR-MGI: Human Inverse Rendering via Jointly Optimizing Geometry, Material, and Illumination
Answer grounding	DDVT: Dynamic Dual-level Vision Transformer Fusion Network for Answer Grounding in Visual Question Answering
Anti-customization	Veiled Diffusion: A Diffusion-Based Anti-Customization Adversarial Attack Method via Semantic Misalignment and Low-Frequency Information
Aperture Radar	The Power of Geometric-Algebra Rotation Composition for Adaptive Filtering
Appearance Embedding	MOT FCG++: Enhanced Representation of Spatio-temporal Motion and Appearance Features
Asymmetric encoder and decoder	An Asymmetric Calibrated Transformer Network for Underwater Image Restoration
Attention	Physics-Guided Deep Learning Framework with Attention for Image Denoising WA-FDNet: A Unified Weight Adaptation Network for Multimodal Image Fusion and Object Detection
Attention Mechanism	BWANet: A low-light image detail enhancement network with multi-scale large receptive fields DAN: Dual-Attention Network for Occlusion-Robust 3D Hand Pose Estimation ENViT-FAS: ENViT with Attack-Oriented Augmentation for Domain-Generalized Face Anti-Spoofing CartoonAnimalPose: A New Dataset and Method for Cartoon Animal Pose Estimation SCAU-Net: An Efficient Module for Multi-scale Feature Extraction and Aggregation in Video Super-Resolution
Attention Mechanisms	Knowledge Graph Completion by Integrating Local and Global Features BIDP: Brain-Inspired Dual-Process CNN-Transformer for Salient Object Detection Cartoon Animation Shading Removal
attention module	Reliable AI-Driven Decision Analysis of Ophthalmic Plastic Surgery Parameters with SparseInst Network Attention-enhanced 3D craniomaxillofacial anatomical landmark detection based on projection
Autonomous Driving	MIC-OPCC: Multi-Indexed Convolution model for Octree Point Cloud Compression
Autonomous Driving Scenes	MC-Gaussian: 3D Gaussian Splatting with Multi-camera in Autonomous Driving
Autonomous Underwater Vehicles	Fuzzy Logic-Based Virtual Leading Path Planning for Autonomous Underwater Vehicles: An Evaluation Index Approach
avatar	PhysAvatar: Physically Plausible Avatar Generation from Sparse Tracking
Avatar Reconstruction	Distilling Complementary Information from Temporal Context for Enhancing Human Appearance in Human-Specific NeRF
B
B-spline	High-Quality Neural Surface Reconstruction from Unoriented Point Clouds via Multilevel Tensor Product B-spline Hash Encoding and Viscosity Regularization
Backdoor Attack	BadHPE: Backdoor Attack for Precise Manipulation of Human Pose Estimation Models
Balanced optimization	Bearing Remaining Useful Life Prediction Using Multimodal Features by Balanced Optimization Between Time-series and Images
Baseball Pitching Biomechanics	On a Dissimilarity Metric for Analyzing Body Synergistic Coordination in Non-Periodic Motion
Batch Processing	PeelMesh: Efficient Interactive Segmentation via Geodesic-Driven Dynamic Topological Updates
Bezier triangle	Bijective Spherical Parameterization via Stereographic Projection
Bidirectional reflectance distribution function	HumanIR-MGI: Human Inverse Rendering via Jointly Optimizing Geometry, Material, and Illumination
Bidirectional wavelet transform	BWANet: A low-light image detail enhancement network with multi-scale large receptive fields
Bijective mapping	Bijective Spherical Parameterization via Stereographic Projection
BiLSTM	SigNet-TAM: Indian Sign Language Recognition with ResNet50-BiLSTM and Temporal Attention Mechanism
Bisector Region	Intrinsic Reflective Symmetry Axis Curve Generation for Meshes
Black-box Attack	Enhancing the Transferability of Adversarial Examples against No-Reference Image Quality Assessment Models
Blockchain	A Privacy-preserving Collaborative 3D Design Framework for Copyright Protection
border features	ViT-BF: Vision Transformer with Border-aware Features for Visual Tracking
boundary alignment	ViT-BF: Vision Transformer with Border-aware Features for Visual Tracking
Boundary optimization	Single Image Shadow Removal using 2D Signed Distance Field
Boundary Representation	CADGCL: Unsupervised Retrieval of CAD Models Via Boundary Representations
Box-level weakly-supervised learning	Adaptive Box-Level Supervision with Superpixel Shape Guidance for Ultrasound Image Segmentation
Brain	PCM-Net: A Hierarchical Medical Image Registration Framework Integrating Channel Adaptability and Multi-Scale Awareness
Brain Tumor Segmentation	LA-mUNet: An Efficient Hybrid CNN-Mamba Network with Lesion Attention for 3D Brain Tumor MRI Segmentation
Brain-computer interaction · Human-centered AI art ·	MindCanvas: A Human-Centric Approach to AI-Driven Artistic Creation Through Brain Signals
Brain-computer interfaces	Real-Time EEG-Based Fear Intensity Estimation for Virtual Reality Exposure Therapy
Brain-Inspired	BIDP: Brain-Inspired Dual-Process CNN-Transformer for Salient Object Detection
Building Design Optimization	Predicting and Optimizing Crowd Evacuations: An Explainable AI Approach
building fire	Deep Learning-based Digital Twin for Real-time Fire Safety Management
C
CAD Model Retrieval	CADGCL: Unsupervised Retrieval of CAD Models Via Boundary Representations
Cadastral parcels	Self-Adaptive Geometric Updating Method for 3D Cadastral Parcels Based on Geometric Algebra
Camouflaged Object Detection	Unified Cross-Domain Refinement Network for Camouflaged Object Detection
Cartoon and anime segmentation	Instance-guided Cartoon Editing with a Curated Large-scale Dataset
Cartoon animal pose estimation	CartoonAnimalPose: A New Dataset and Method for Cartoon Animal Pose Estimation
cartoon animation	Cartoon Animation Shading Removal
Cartoon editing	Instance-guided Cartoon Editing with a Curated Large-scale Dataset
cartoon image	Line Drawing Abstraction Based on Line Importance Evaluation
Cartoon style manipulation	Instance-guided Cartoon Editing with a Curated Large-scale Dataset
Caustics	Batch Specular Manifold Sampling for Caustics Rendering
Channel Attention	Task-adaptive Channel Attention Graph Network for Few-shot 3D Point Cloud Classification Enhancing Nvshu Recognition Based on Polarity-aware Linear Attention and Learnable Local Salient Kernel
ChatGPT	Towards Culturally Aware AI: Quantified Evaluation of Relevance and Similarity in AI-Generated Images
Circular Splines	Coordinate Free Circular Splines
Classifier-free guidance	Text-driven High-quality 3D Human Generation via Variational Gradient Estimationl and Latent Reward Models
Classroom scene	Weakly Semi-supervised Classroom Teacher Visual Tracking by Single-point Annotations
Clifford	Clifford(11,1) String Theory
Clifford algebra	Keynote: Geometric Algebra in Electrical Engineering: A Comprehensive Review of Power Systems Applications Explicit Formula for Inverse and Determinant in Geometric Algebras over Seven-dimensional Vector Spaces Hypercomplexification of U-Net by Clifford Algebra Embeddings
Cloud Rendering	Optimisation of Web-Edge-Cloud Intelligent Collaborative Rendering System For Dynamic Web3D Scenes
Clustering Association	MOT FCG++: Enhanced Representation of Spatio-temporal Motion and Appearance Features
co-speech gesture generation	A Two Stage Controllable Co-Speech Gesture Generation Method FaceCapGes: Real-Time Frame-by-Frame Gesture Generation from Audio, Facial Capture, and Head Pose
Coarse to fine	Coordinate-Aware Implicit Image Function for Arbitrary-Scale Image Super-Resolution
Coherent rays	Direct Coherent Ray Generation for Path Tracing
Coincidence Site	A Geometric Algebra Approach to Coincidence Site Lattices
Collaboration	Optimisation of Web-Edge-Cloud Intelligent Collaborative Rendering System For Dynamic Web3D Scenes
Collaborative design	A Privacy-preserving Collaborative 3D Design Framework for Copyright Protection
color image privacy protection	Privacy Image Secrecy Scheme Based on Chaos-Driven FSM and FQM
Complex geometric algebra	Notes on Quantum Computing over Complex Geometric Algebras with Split Signature
Complex Night Scene	IG-Diff: Complex Night Scene Restoration with Illumination-Guided Diffusion Model
computational imaging	SDOD: Towards Reliable Object Detection under Diverse Rainy Conditions with Deraining and Mutual Learning
Computational Perception	A Visual Self-attention Mechanism Facial Expression Recognition Network beyond Convnext
Computer Graphics	Keynote: Curves on Spheres, the Geometric Algebra Approach
Computer Vision	Alphanumeric Fingerspelling: A New Large-Scale Dataset and Comparative Analysis of Methods for Indian Sign Language GeloVec: Higher Dimensional Geometric Smoothing for Coherent Visual Feature Extraction in Image Segmentation
computing determinant	Explicit Formula for Inverse and Determinant in Geometric Algebras over Seven-dimensional Vector Spaces
computing inverse	Explicit Formula for Inverse and Determinant in Geometric Algebras over Seven-dimensional Vector Spaces
Concrete Performance	Geometric Algebra for Cryptography and Artificial Intelligence: Demonstrating Concrete Performance and Expressiveness Advantages
Conformal Geometric Algebra	Neural-GASh: A CGA-Based Neural Radiance Prediction Pipeline for Real-Time Shading
Conformal Geometric Algebra	Keynote: Conformal Geometric Algebra for Spherical Shell Intersections
Context-Aware	Dynamic Prompting and Cross-Modal Attention for Context-Aware Multimodal Emotion Recognition
Continuous Line Drawing	Image Halftoning Using a Single Closed Non-self-intersecting Curve
Continuous sign language recognition	VS-DSN: Variable-Speed Dual-Stream Network for Continuous Sign Language Recognition
Contrast Information	Efficient Document Shadow Removal with Contrast-Aware Guidance
Contrastive Graph Learning	CADGCL: Unsupervised Retrieval of CAD Models Via Boundary Representations
Contrastive Learning	Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions An Industrial Multi-Machining Feature Dataset and Contrastive Learning-based Network for Feature Recognition
Control	Guiding Steady Fluid Flow with Terrain-Based Repulsive Forces
Conversational Virtual Agents	Hi-Reco: High-Fidelity Real-Time Conversational Digital Humans
ConvLSTM	Sequential Fluid Image Generation Network Based on Spatio-Temporal Swin Transformer
Convolution-Based Motion Analysis	On a Dissimilarity Metric for Analyzing Body Synergistic Coordination in Non-Periodic Motion
Convolutional block attention module	An Improved Small Object Detection Method for Shuttlecock Activity Analysis
convolutional neural network	A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images
Convolutional Neural Networks	Knowledge Graph Completion by Integrating Local and Global Features LA-mUNet: An Efficient Hybrid CNN-Mamba Network with Lesion Attention for 3D Brain Tumor MRI Segmentation
Coordinate	Coordinate Free Circular Splines
Coordinate Systems	Curvilinear Coordinate Systems for 3D Design
Coordinate-free quaternionic polynomials	Keynote: Normal Forms of Coordinate-Free Quaternionic Polynomials
Copyright protection	A Privacy-preserving Collaborative 3D Design Framework for Copyright Protection
correspondence	RegistrationBooster: Enhancing Rigid Registration Performance through Correspondence Refinement ODFM: Orientation-Aware Dual-Branch Functional Maps for Unsupervised Non-rigid Shape Matching
Crop disease classification	Generating Multi-Illumination Leaf Images through Single-Image Material Estimation for Robust Disease Recognition
Cross pseudo supervision	Adaptive Box-Level Supervision with Superpixel Shape Guidance for Ultrasound Image Segmentation
Cross-domain learning	CartoonAnimalPose: A New Dataset and Method for Cartoon Animal Pose Estimation
Cross-entropy loss	UNet-3D with Adaptive TverskyCE Loss for Pancreas Medical Image Segmentation
cross-Layer feature	Cross-Layer Feature Aggregation Object Detection Networks for Modality-enhanced UAV Images
Cross-Modal Attention	Dynamic Prompting and Cross-Modal Attention for Context-Aware Multimodal Emotion Recognition
Cross-Modal Fusion	Semantic-Orthogonal Multi-modal Attention Network for RGB-D Salient Object Detection
Cross-modality	MDSAM: Intrinsic Cues Guided Segmentation for Mirror Detection
Crowd Prediction	Predicting and Optimizing Crowd Evacuations: An Explainable AI Approach
Crowd Simulation	Predicting and Optimizing Crowd Evacuations: An Explainable AI Approach
cryptography	Privacy Image Secrecy Scheme Based on Chaos-Driven FSM and FQM
Cultural Analysis	Towards Culturally Aware AI: Quantified Evaluation of Relevance and Similarity in AI-Generated Images
Curvature	Turbulence Estimation in Smoke Simulation via Curvature-Based Image Features
Curve reconstruction	ConDT: A 2D curve reconstruction algorithm based on a constrained-neighbor proximity graph
Curvilinear	Curvilinear Coordinate Systems for 3D Design
D
Dark channel loss	A continuous test-time adaptation method for dynamic haze removal
Data augmentation	Enhancing Small Object Detection in Aerial Images Under Multi-Weather Conditions Using Modified YOLO CoFormer:Coupling Attentive Model for Visual Sentiment Analysis with Hierarchical Emotion Loss A continuous test-time adaptation method for dynamic haze removal
Data Compression	MIC-OPCC: Multi-Indexed Convolution model for Octree Point Cloud Compression
data generation	Enhancing INR-based Super-Resolution Performance in Scientific Visualization via a Priori and a Posteriori Constraints
Data Poisoning	BadHPE: Backdoor Attack for Precise Manipulation of Human Pose Estimation Models
Dataset Creation	Alphanumeric Fingerspelling: A New Large-Scale Dataset and Comparative Analysis of Methods for Indian Sign Language
Deep functional map	TriAlign: Revisiting Deep Functional Map from Map Representation Alignment Perspectives
Deep Learning	Person-In-Situ: Scene-Consistent Human Image Insertion with Occlusion-Aware Pose Control Deep Learning-based Digital Twin for Real-time Fire Safety Management Advancements and Challenges of Deep Learning in Virtual Try-On: A Comprehensive Review TerraFusion: Joint Generation of Terrain Shape and Texture Using Latent Diffusion Models MELD: A Multi-Element Latent Diffusion Model for Urban Greenspace Layout Generation Coordinate-Aware Implicit Image Function for Arbitrary-Scale Image Super-Resolution GeloVec: Higher Dimensional Geometric Smoothing for Coherent Visual Feature Extraction in Image Segmentation Sequential Fluid Image Generation Network Based on Spatio-Temporal Swin Transformer Dynamic Style-Adaptive Image Transformation Network Exploring Procedural Content Generation of 3D City Scenes for 2D Semantic Segmentation EX-YOLO: Improve YOLOv11 to achieve efficient detection of small targets of drones
Deep learning · Image Processing and	Boosting Remote Semantic Segmentation Using Vision-and- language Foundation Model
Defocus region detection	A Novel Approach to Defocus Region Detection in Phase-Shifting Structured Light 3D Reconstruction
Deformable convolution	PPVSR:Video Super-Resolution Reconstruction Algorithms Based on Progressive Processing
Delaunay triangulation	ConDT: A 2D curve reconstruction algorithm based on a constrained-neighbor proximity graph
Dependency Coefficient	Enhancing Single-View 3D Clothed Human Reconstruction with Hybrid Prior Integration
Depth Completion	L2H-NeRF: Low- to High-Frequency-Guided NeRF for 3D Reconstruction With a Few Input Scenes
Depth estimation	DOMVS:Unsupervised Multi-View Stereo for Dealing With Occlusion Scenes Multi-Scale Attention and Adaptive Self-Attention for Occlusion-Aware Depth Estimation in Light Field
Dictionary Learning	DL-DETR: Exploring the Future Directions of Fusion Between Dictionary Learning and DETR
Differentiable Rendering	Texture and Geometry Optimization for 3D Reconstruction
Differential Geometry Processing	Locality-Preserving Free-Form Deformation
Diffusion	A Two Stage Controllable Co-Speech Gesture Generation Method
Diffusion Model	Person-In-Situ: Scene-Consistent Human Image Insertion with Occlusion-Aware Pose Control SemanticAvatar: Human Surface Reconstruction Based on Semantically Consistent Biplane Features SelfAge: Personalized Facial Age Transformation Using Self-reference Images Geometry Guidance Diffusion Image Morphing with Large Shape Difference TerraFusion: Joint Generation of Terrain Shape and Texture Using Latent Diffusion Models Latent Interpretation for Multi-View Face Synthesis across GAN and Diffusion via Conditional Reconstruction MIGEdit: Multimodal Interactive Garment Editing FusionCraft: A New Paradigm for Fine-Grained Multimodal Fashion Design Generation
Diffusion models	StyleRegLoRA: An Improved Framework for SDXL LoRA Fine-tuning Towards Art Category Generation Veiled Diffusion: A Diffusion-Based Anti-Customization Adversarial Attack Method via Semantic Misalignment and Low-Frequency Information
Diffusion-based Restoration Model	IG-Diff: Complex Night Scene Restoration with Illumination-Guided Diffusion Model
DiffusionNet · Approximate basis · Scalable-ZoomOut ·	EDiffNet: An Enhanced DiffusionNet for Non-isometric 3D Shape Correspondence and Matching
Digital Geometry Processing	PeelMesh: Efficient Interactive Segmentation via Geodesic-Driven Dynamic Topological Updates
digital halftoning	Accelerating Error Diffusion Halftoning for High-Throughput Wide-Format Industrial Printing
Digital Humans	The Evolution of Digital Humans: Past, Present, and the Road Ahead
digital twin	Deep Learning-based Digital Twin for Real-time Fire Safety Management
Dilated UNet-3D	UNet-3D with Adaptive TverskyCE Loss for Pancreas Medical Image Segmentation
Dimensional Submanifold	Clifford(11,1) String Theory
Direct and Indirect Manipulation	Locality-Preserving Free-Form Deformation
Direction reuse	Direct Coherent Ray Generation for Path Tracing
Directional attention	Facial Action Unit Detection with Iterative Rank Reduction Adapter and Directional Attention
Disaster Medical Response	Prototype XR Elastodynamics System for Disaster Medical Response
Distance Geometry	Keynote: Conformal Geometric Algebra for Spherical Shell Intersections
Distinctive Regions	Attention-Guided Self-Supervised Distinctive Region Detection in Point Clouds
Document Enhancement	Efficient Document Shadow Removal with Contrast-Aware Guidance
Document Shadow Removal	Efficient Document Shadow Removal with Contrast-Aware Guidance
domain adaptation	SDOD: Towards Reliable Object Detection under Diverse Rainy Conditions with Deraining and Mutual Learning
domain adaption	A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images
domain gap	A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images
Domain generalization	ENViT-FAS: ENViT with Attack-Oriented Augmentation for Domain-Generalized Face Anti-Spoofing
Dual teacher knowledge distillation	DTKD-UIE: Underwater Image Enhancement based on Dual Teacher knowledge distillation
Dual-Branch SSM-CNN Feature Extractor	IMFDM: Improved Mamba-based Feature Decomposition Model for Multi-Modality Image Fusion
Dual-Stream	VS-DSN: Variable-Speed Dual-Stream Network for Continuous Sign Language Recognition
Dynamic network	DDVT: Dynamic Dual-level Vision Transformer Fusion Network for Answer Grounding in Visual Question Answering
Dynamic Texture Attention	YOLO-Pest A Model Design for Crop Pest Detection
Dynamic Time Warping	Interpretable Two-Stage Action Quality Assessment via 3D Human Pose Estimation and Dynamic Feature Alignment
Dynamic Topology Updates	PeelMesh: Efficient Interactive Segmentation via Geodesic-Driven Dynamic Topological Updates
Dynamic Translational Gains	Dynamic Translational Gains Manipulation for Tiny Object Interaction
Dynamic voxel grid	Dynamic voxel grid optimization for high-fidelity rgb-d supervised surface reconstruction
E
ECG synthesis	Generation of Realistic Synthetic ECG using Uncertainty-Aware Diffusion Model
Edge Computing	Optimisation of Web-Edge-Cloud Intelligent Collaborative Rendering System For Dynamic Web3D Scenes
edge information	Cross-Layer Feature Aggregation Object Detection Networks for Modality-enhanced UAV Images
EEG	Real-Time EEG-Based Fear Intensity Estimation for Virtual Reality Exposure Therapy
Efficiency	SCAU-Net: An Efficient Module for Multi-scale Feature Extraction and Aggregation in Video Super-Resolution
Elastic Dynamics	Enhanced Material Point Method with Affine Projection Stabilizer for Efficient Hyperelastic Simulations
Elastodynamics Simulations	Prototype XR Elastodynamics System for Disaster Medical Response
Elastoplasticity clay	Real-Time Immersive Haptic Sculpting with Elastoplastic Virtual Clay
Electrical Curves	Keynote: Geometric Algebra in Electrical Engineering: A Comprehensive Review of Power Systems Applications
Electrocardiogram	Bimodal VIT Adaptive Cross-Fusion Micro-Expression Recognition Based on ECG-QRS Waves
Embedding of fused scheme	UTFusion: A General Image Fusion Framework with a Unified Transformer
EMCAD	RaEUNet: A Retentive and Efficient UNet for Medical Image Segmentation
Emergency Response	Towards Extended Reality in Emergency Response: Guidelines and Challenges for First Responder Friendly Augmented Interfaces
Emotion Estimation	EE-Head: Emotion Estimation for Precise Facial Expression in NeRF Head Avatars
Emotion expression · Dynamic AI art	MindCanvas: A Human-Centric Approach to AI-Driven Artistic Creation Through Brain Signals
emotion intensity perception	Decoding Emotions: How Eye Features Influence Perception of Emotional Intensity in Virtual Characters
Emotion Recognition	Dynamic Prompting and Cross-Modal Attention for Context-Aware Multimodal Emotion Recognition
Emotional impression	Machine Learning Approach for Color Selection near Light/Dark Boundaries Considering Emotional Impressions
Entropy-guided Pseudo Label Generation	PLNet: Entropy-Guided Pseudo Label Refinement with Sensitivity-Specificity Enhancement for Medical Image Segmentation
epsilon sampling	ConDT: A 2D curve reconstruction algorithm based on a constrained-neighbor proximity graph
Equivariance	Few-shot Medical Image Segmentation via Query Transformation Learning
error diffusion	Accelerating Error Diffusion Halftoning for High-Throughput Wide-Format Industrial Printing
Evaluation Index	Fuzzy Logic-Based Virtual Leading Path Planning for Autonomous Underwater Vehicles: An Evaluation Index Approach
Evaluation Methods	Towards Culturally Aware AI: Quantified Evaluation of Relevance and Similarity in AI-Generated Images
experience optimization	Obstacle Avoidance Strategy Based on Spatial Contraction for Multi-User Redirected Walking
Explainability	Predicting and Optimizing Crowd Evacuations: An Explainable AI Approach
exponentials of Okubo units	Contemplating Susumu Okubo's Algebra of Quantum Color Dynamics
Extended Reality	Towards Extended Reality in Emergency Response: Guidelines and Challenges for First Responder Friendly Augmented Interfaces
Extract Detailed	A Visual Self-attention Mechanism Facial Expression Recognition Network beyond Convnext
eye features	Decoding Emotions: How Eye Features Influence Perception of Emotional Intensity in Virtual Characters
F
Fabrication	StencilQR: Connectivity-enhanced Fabricable QR Codes for Stencil
Face Anti-spoofing	ENViT-FAS: ENViT with Attack-Oriented Augmentation for Domain-Generalized Face Anti-Spoofing
Face editing	Latent Interpretation for Multi-View Face Synthesis across GAN and Diffusion via Conditional Reconstruction
Face photo-sketch synthesis	Face Sketch Synthesis via Sparse Spatial Channel Generators and Multi-Scale Discriminators
face recognition	Recognize Me If You Can: Two-stream Adversarial Transfer for Facial Privacy Protection using Fine-grained Makeup
face-capture	FaceCapGes: Real-Time Frame-by-Frame Gesture Generation from Audio, Facial Capture, and Head Pose
Facial action unit detection	Facial Action Unit Detection with Iterative Rank Reduction Adapter and Directional Attention
Facial Expression Recognition	A Visual Self-attention Mechanism Facial Expression Recognition Network beyond Convnext
facial privacy protection	Recognize Me If You Can: Two-stream Adversarial Transfer for Facial Privacy Protection using Fine-grained Makeup
Fashion Image Generation	D^2-Diff: Controllable Fashion Image Generation with Disentangled Style and Content
Fast Fourier Transform	Single Image Shadow Removal using 2D Signed Distance Field
Feature extraction	PPVSR:Video Super-Resolution Reconstruction Algorithms Based on Progressive Processing
Feature Extraction and Matching	L2H-NeRF: Low- to High-Frequency-Guided NeRF for 3D Reconstruction With a Few Input Scenes
feature fusion	EX-YOLO: Improve YOLOv11 to achieve efficient detection of small targets of drones
feature matching	A Novel Registration Framework For Large-scale Point Clouds via Geometric Salience Computation
feature pyramid network	EX-YOLO: Improve YOLOv11 to achieve efficient detection of small targets of drones
Few-shot Learning	Efficient selective labeling strategies for enhanced few-shot 3D point cloud semantic segmentation Task-adaptive Channel Attention Graph Network for Few-shot 3D Point Cloud Classification
Few-shot medical image segmentation	Few-shot Medical Image Segmentation via Query Transformation Learning
Fine-Grained	Enhancing Vision Transformer for Fine-Grained Classification with Selective Attention Aggregation and Multi-Head Noise Suppression
fine-grained feature distillation	Lightweight Image Super-Resolution Using Fine-Grained Feature Distillation in a Dense Residual U-Net
Fine-grained Features	PortraitFormer: Global Illumination Helps Portrait Shadow Removal
Fine-tuning	StyleRegLoRA: An Improved Framework for SDXL LoRA Fine-tuning Towards Art Category Generation
Fingerspelling Recognition	Alphanumeric Fingerspelling: A New Large-Scale Dataset and Comparative Analysis of Methods for Indian Sign Language
First Responders	Towards Extended Reality in Emergency Response: Guidelines and Challenges for First Responder Friendly Augmented Interfaces
fish motion skeleton	Generating 3D fish motion skeleton via iterative optimization method and FishSkeletonNet
fish posture	Generating 3D fish motion skeleton via iterative optimization method and FishSkeletonNet
Fluid Dynamics	Sequential Fluid Image Generation Network Based on Spatio-Temporal Swin Transformer
Fluid simulation	Turbulence Estimation in Smoke Simulation via Curvature-Based Image Features Extending Implicit Density Projection for Multiphase Fluids
Foundation Models	PDFT: Parameter-Diminish Fine-Tuning for Transformer-based Models
FPGA	Accelerating Error Diffusion Halftoning for High-Throughput Wide-Format Industrial Printing
Frame alignment	PPVSR:Video Super-Resolution Reconstruction Algorithms Based on Progressive Processing
Free	Coordinate Free Circular Splines
Free-form Deformation	Locality-Preserving Free-Form Deformation
Frequency Domain	Unified Cross-Domain Refinement Network for Camouflaged Object Detection
Frequency domain information	DTKD-UIE: Underwater Image Enhancement based on Dual Teacher knowledge distillation
Front-and-back Garment Panoramic 3D	PG-VTON: Front-and-Back Garment Guided Panoramic Gaussian Virtual Try-On with Diffusion Modeling
Fuzzy Logic Control	Fuzzy Logic-Based Virtual Leading Path Planning for Autonomous Underwater Vehicles: An Evaluation Index Approach
G
GA Code Generation	GA-VisAgent: A Multi-Agent Application for Code Generation and Visualization in Interactive Learning
GA Visualization	GA-VisAgent: A Multi-Agent Application for Code Generation and Visualization in Interactive Learning
GAALOP	Symbolically Optimized Characteristic Multivector Rotor Estimation for 3D Point Cloud Registration
Gait dataset	Graph Convolutional Networks for 3D Skeleton-Based Scoliosis Screening Using Gait Sequences
Game Engine	Neural-GASh: A CGA-Based Neural Radiance Prediction Pipeline for Real-Time Shading
game engines	Exploring Procedural Content Generation of 3D City Scenes for 2D Semantic Segmentation
GAN	Latent Interpretation for Multi-View Face Synthesis across GAN and Diffusion via Conditional Reconstruction
Garment editing	MIGEdit: Multimodal Interactive Garment Editing
garment modeling	GartransNet: 3D garments animation via transmission optimized networks
Gaussian Splatting	PG-VTON: Front-and-Back Garment Guided Panoramic Gaussian Virtual Try-On with Diffusion Modeling GenericAvatar: Generic Human Modeling from Monocular Video Based on Mesh-guided Gaussians Feature Replacement in Gaussian Splatting for 3D Stylization
Generative Adversarial Network	Reproducing the Appearance of Metallic Materials by Capturing Long-Range Dependencies using Image-to-Image Translation Network with Vision Transformer
Generative AI	Generative GeoSpatial Artificial Intelligence with Geometric Algebra Towards Generative Filming: Progress and Challenges
Generative Filming	Towards Generative Filming: Progress and Challenges
generative Models	Advancements and Challenges of Deep Learning in Virtual Try-On: A Comprehensive Review Towards Culturally Aware AI: Quantified Evaluation of Relevance and Similarity in AI-Generated Images
Geo dataset	GUM-DiT: A Foundation Model for Generating Urban Morphological Layouts
Geometric Algebra	Keynote: Geometric Algebra in Electrical Engineering: A Comprehensive Review of Power Systems Applications Explicit Formula for Inverse and Determinant in Geometric Algebras over Seven-dimensional Vector Spaces GA-VisAgent: A Multi-Agent Application for Code Generation and Visualization in Interactive Learning GeloVec: Higher Dimensional Geometric Smoothing for Coherent Visual Feature Extraction in Image Segmentation Geometric Algebra-Based Time Series Reconstruction of Sea Level Variability – A Case Study Along the Northeast Pacific Coast (1993-2023) Geometric Algebra for Quadrics Symbolically Optimized Characteristic Multivector Rotor Estimation for 3D Point Cloud Registration Notes on Quantum Computing over Complex Geometric Algebras with Split Signature Generative GeoSpatial Artificial Intelligence with Geometric Algebra
Geometric Algebra	Keynote: Curves on Spheres, the Geometric Algebra Approach The Power of Geometric-Algebra Rotation Composition for Adaptive Filtering Geometric Algebra and Mechanism Theory Geometric Algebra: An Overview About Different Implementation Representations and Memory Requirements
Geometric Algebra Approach	A Geometric Algebra Approach to Coincidence Site Lattices
Geometric Algebra for AI	Geometric Algebra for Cryptography and Artificial Intelligence: Demonstrating Concrete Performance and Expressiveness Advantages
Geometric Algebra for Cryptography	Geometric Algebra for Cryptography and Artificial Intelligence: Demonstrating Concrete Performance and Expressiveness Advantages
Geometric Algebra for Quadrics	Geometric Algebra for Quadrics
Geometric Application	Keynote: Curves on Spheres, the Geometric Algebra Approach
geometric constraints	GartransNet: 3D garments animation via transmission optimized networks
Geometric Deep Learning	SpectralVAE: spectral variational autoencoder for 3D mesh representation learning
Geometric Guidance	Geometry Guidance Diffusion Image Morphing with Large Shape Difference
Geometric Representation Learning	GeloVec: Higher Dimensional Geometric Smoothing for Coherent Visual Feature Extraction in Image Segmentation
geometric salience	A Novel Registration Framework For Large-scale Point Clouds via Geometric Salience Computation
Geometric Theory	Geometric Algebra and Mechanism Theory
geometric voting	A Novel Registration Framework For Large-scale Point Clouds via Geometric Salience Computation
Geometry updating	Self-Adaptive Geometric Updating Method for 3D Cadastral Parcels Based on Geometric Algebra
Geometry-Enhanced Two-Branch	UMan: Multi-Scale Feature Reconstruction and Super-Resolution for Single-Image 3D Human Modeling
GeoSpatial Intelligence	Generative GeoSpatial Artificial Intelligence with Geometric Algebra
Global and Local Modeling	Boosting Memory Network for Video Object Segmentation in Complex Scenes
Global illumination	Multilevel Monte Carlo for Asymptotically Efficient Path Tracing Optimisation of Web-Edge-Cloud Intelligent Collaborative Rendering System For Dynamic Web3D Scenes
Global Illumination Balancing	PortraitFormer: Global Illumination Helps Portrait Shadow Removal
Gr\"obner basis	Keynote: Normal Forms of Coordinate-Free Quaternionic Polynomials
Gradient modulation	Bearing Remaining Useful Life Prediction Using Multimodal Features by Balanced Optimization Between Time-series and Images
Granular Materials	Adaptive Sampling for Interactive Simulation of Granular Material
Graph convolutional networks	Graph Convolutional Networks for 3D Skeleton-Based Scoliosis Screening Using Gait Sequences
Graph neural network	Knowledge Graph Completion by Integrating Local and Global Features
Graph structure learning	MAS-KCL: Knowledge Component Graph Structure Learning with Large Language Model-based Agentic Workflow
H
hand depth images	DAN: Dual-Attention Network for Occlusion-Robust 3D Hand Pose Estimation
Hand pose estimation	DAN: Dual-Attention Network for Occlusion-Robust 3D Hand Pose Estimation
Haptics rendering	Real-Time Immersive Haptic Sculpting with Elastoplastic Virtual Clay
Harmonic Analysis	Keynote: Geometric Algebra in Electrical Engineering: A Comprehensive Review of Power Systems Applications
Head Avatar	EE-Head: Emotion Estimation for Precise Facial Expression in NeRF Head Avatars
Height Field	RelieFormer:End-to-End Bas Relief Generation via Transformer
Hessian energy	High-Quality Neural Surface Reconstruction from Unoriented Point Clouds via Multilevel Tensor Product B-spline Hash Encoding and Viscosity Regularization
Hierarchy Fusion	RainRWKV: A Deep RWKV Model for Video Deraining
High-dimensional Geometric Algebra	Geometric Algebra for Quadrics
High-Fidelity Digital Humans	Hi-Reco: High-Fidelity Real-Time Conversational Digital Humans
High-Fidelity Garment Design	FusionCraft: A New Paradigm for Fine-Grained Multimodal Fashion Design Generation
Homophone Distinguish	VCHFC: Visual-Content Hybrid Feature Cue Module for Lipreading
Human eye feature detection	Reliable AI-Driven Decision Analysis of Ophthalmic Plastic Surgery Parameters with SparseInst Network
human motion estimation	Robust bi-level optimization for monocular human and scene reconstruction
human pose	GartransNet: 3D garments animation via transmission optimized networks
Human Pose Estimation	BadHPE: Backdoor Attack for Precise Manipulation of Human Pose Estimation Models
human scene interaction	Robust bi-level optimization for monocular human and scene reconstruction
Human Surface Reconstruction	SemanticAvatar: Human Surface Reconstruction Based on Semantically Consistent Biplane Features
Human-Centered Computing	Towards Extended Reality in Emergency Response: Guidelines and Challenges for First Responder Friendly Augmented Interfaces
human-computer interaction	DAN: Dual-Attention Network for Occlusion-Robust 3D Hand Pose Estimation
Human-Object Interaction	Learning Human-Object Interactions in Videos with Optical Flow
Human-Robot Interaction	From Sci-Fi to Reality: Exploring Teenagers' Perceptions and Ideas of AI Robots
Hybrid Attention	AMNet: An Attention-Enhanced Multi-Branch Network for Micro-Expression Recognition CoFormer:Coupling Attentive Model for Visual Sentiment Analysis with Hierarchical Emotion Loss
Hybrid Attention Attention Mechanism	Transforming Time and Space: Efficient Video Super-Resolution with Hybrid Attention and Deformable Transformers
Hyperplane	OSH-Splat: Optimizable Semantic Hyperplanes for Enhanced 3D Language Feature Gaussian Splatting
I
Illumination	Malicious Manipulation of Incident Light: Enabling Adversarial Relighting Attack with Physical Interpretability
Illumination Consistency	Reproducing the Appearance of Metallic Materials by Capturing Long-Range Dependencies using Image-to-Image Translation Network with Vision Transformer
Illumination Guided Module	IG-Diff: Complex Night Scene Restoration with Illumination-Guided Diffusion Model
Illustration coloring	Machine Learning Approach for Color Selection near Light/Dark Boundaries Considering Emotional Impressions
Image Classification	Enhancing Vision Transformer for Fine-Grained Classification with Selective Attention Aggregation and Multi-Head Noise Suppression
Image Composition	Person-In-Situ: Scene-Consistent Human Image Insertion with Occlusion-Aware Pose Control
Image dehazing	A continuous test-time adaptation method for dynamic haze removal
Image denoising	Physics-Guided Deep Learning Framework with Attention for Image Denoising
Image deraining	An Effective Wavelet Neural Network for Ultra-High-Definition Image Deraining
Image Editing	Person-In-Situ: Scene-Consistent Human Image Insertion with Occlusion-Aware Pose Control SelfAge: Personalized Facial Age Transformation Using Self-reference Images
Image enhancement	An Asymmetric Calibrated Transformer Network for Underwater Image Restoration
Image fusion	WA-FDNet: A Unified Weight Adaptation Network for Multimodal Image Fusion and Object Detection UTFusion: A General Image Fusion Framework with a Unified Transformer
Image generation	MIGEdit: Multimodal Interactive Garment Editing
Image Halftoning	Image Halftoning Using a Single Closed Non-self-intersecting Curve
image inpainting	Robust bi-level optimization for monocular human and scene reconstruction
Image Morphing	Geometry Guidance Diffusion Image Morphing with Large Shape Difference
Image Processing and Analysis	Hybrid-SANet: Hybrid Self-Attention Transformer for Efficient Image Super-Resolution
Image restoration	Coordinate-Aware Implicit Image Function for Arbitrary-Scale Image Super-Resolution
Image segmentation	Unified Cross-Domain Refinement Network for Camouflaged Object Detection
Image Steganography	DualShield: Dual-Layer Protection for Secure and Robust Stable Diffusion Steganography
Image super-resolution	Lightweight Image Super-Resolution Using Fine-Grained Feature Distillation in a Dense Residual U-Net
Image Synthesis	TerraFusion: Joint Generation of Terrain Shape and Texture Using Latent Diffusion Models Generating Multi-Illumination Leaf Images through Single-Image Material Estimation for Robust Disease Recognition
Image-based Rendering	Towards Generative Filming: Progress and Challenges
Image-to-Image Translation	Reproducing the Appearance of Metallic Materials by Capturing Long-Range Dependencies using Image-to-Image Translation Network with Vision Transformer
Image/Video Stylization	Dynamic Style-Adaptive Image Transformation Network
Immersive virtual sculpting	Real-Time Immersive Haptic Sculpting with Elastoplastic Virtual Clay
Implementation Representations	Geometric Algebra: An Overview About Different Implementation Representations and Memory Requirements
Implicit field	Video Sketching using Multi-domain Guidance and Implicit Encoding
Implicit image function	Coordinate-Aware Implicit Image Function for Arbitrary-Scale Image Super-Resolution
implicit neural representation	Enhancing INR-based Super-Resolution Performance in Scientific Visualization via a Priori and a Posteriori Constraints
Implicit shells	ImS: Implicit Shell for the Sandwich-Walled Space Surrounding Polygonal Meshes
Implicit surface rendering	HumanIR-MGI: Human Inverse Rendering via Jointly Optimizing Geometry, Material, and Illumination
Improved Mamba-based Feature Decomposition Model	IMFDM: Improved Mamba-based Feature Decomposition Model for Multi-Modality Image Fusion
Indian Sign Language	Alphanumeric Fingerspelling: A New Large-Scale Dataset and Comparative Analysis of Methods for Indian Sign Language SigNet-TAM: Indian Sign Language Recognition with ResNet50-BiLSTM and Temporal Attention Mechanism
Indirect illumination	HumanIR-MGI: Human Inverse Rendering via Jointly Optimizing Geometry, Material, and Illumination
Instance segmentation	An Industrial Multi-Machining Feature Dataset and Contrastive Learning-based Network for Feature Recognition
Interactive editing	MIGEdit: Multimodal Interactive Garment Editing
Interactive Mesh Segmentation	PeelMesh: Efficient Interactive Segmentation via Geodesic-Driven Dynamic Topological Updates
Interactive Segmentation	Building 3DGS Representation for Single Interested Object via Joint Segmentation-training Framework
Interior layout	Exploring Structural Lines for Interior Floorplan Segmentation
Interpretable Movement Behavior	Scene-Enhanced Social Interpretable Movement Behavior for Multimodal Pedestrian Trajectory Prediction
Intrinsic Symmetry Axis Curve	Intrinsic Reflective Symmetry Axis Curve Generation for Meshes
Invariance	Few-shot Medical Image Segmentation via Query Transformation Learning
Inverse Kinematics	A Two Stage Controllable Co-Speech Gesture Generation Method
Inverse rendering	Malicious Manipulation of Incident Light: Enabling Adversarial Relighting Attack with Physical Interpretability HumanIR-MGI: Human Inverse Rendering via Jointly Optimizing Geometry, Material, and Illumination Generating Multi-Illumination Leaf Images through Single-Image Material Estimation for Robust Disease Recognition
Invertible neural network	Embedding Space Decomposition Meets Invertible Networks: A New Paradigm for Unpaired Low-Light Enhancement
IoU	Small Object Detection Algorithm with Selective Fusion of Small Scale Features
IoU-aware classification score	TADT: Task-aligned Deep Tracking
IPFS	A Privacy-preserving Collaborative 3D Design Framework for Copyright Protection
Iterative Closest Point	Symbolically Optimized Characteristic Multivector Rotor Estimation for 3D Point Cloud Registration
iterative optimization	Generating 3D fish motion skeleton via iterative optimization method and FishSkeletonNet
Iterative rank reduction adapter	Facial Action Unit Detection with Iterative Rank Reduction Adapter and Directional Attention
J
Joint Optimization	Texture and Geometry Optimization for 3D Reconstruction
K
Knowledge component	MAS-KCL: Knowledge Component Graph Structure Learning with Large Language Model-based Agentic Workflow
Knowledge Graph	Knowledge Graph Completion by Integrating Local and Global Features
Knowledge graph completion	Knowledge Graph Completion by Integrating Local and Global Features
L
l-systems	Exploring Procedural Content Generation of 3D City Scenes for 2D Semantic Segmentation
Landmark Detection	Attention-enhanced 3D craniomaxillofacial anatomical landmark detection based on projection
Large kernel convolution	BWANet: A low-light image detail enhancement network with multi-scale large receptive fields
Large language model	A Two Stage Controllable Co-Speech Gesture Generation Method MAS-KCL: Knowledge Component Graph Structure Learning with Large Language Model-based Agentic Workflow MatLayerNet: A Multi-Agent-Based Method for Text-to-PBR Material Generation
Large language models	GA-VisAgent: A Multi-Agent Application for Code Generation and Visualization in Interactive Learning
Large Shape Difference	Geometry Guidance Diffusion Image Morphing with Large Shape Difference
Latent Diffusion Models	DualShield: Dual-Layer Protection for Secure and Robust Stable Diffusion Steganography
Lattices	A Geometric Algebra Approach to Coincidence Site Lattices
Layout Generation	MELD: A Multi-Element Latent Diffusion Model for Urban Greenspace Layout Generation
Layout pattern learning	GUM-DiT: A Foundation Model for Generating Urban Morphological Layouts
Lesion Attention	LA-mUNet: An Efficient Hybrid CNN-Mamba Network with Lesion Attention for 3D Brain Tumor MRI Segmentation
LiDAR	MIC-OPCC: Multi-Indexed Convolution model for Octree Point Cloud Compression
Light field image	Multi-Scale Attention and Adaptive Self-Attention for Occlusion-Aware Depth Estimation in Light Field
Light-weight Super-Resolution	Hybrid-SANet: Hybrid Self-Attention Transformer for Efficient Image Super-Resolution
Lightweight Design	LA-mUNet: An Efficient Hybrid CNN-Mamba Network with Lesion Attention for 3D Brain Tumor MRI Segmentation
line drawing abstraction	Line Drawing Abstraction Based on Line Importance Evaluation
line drawing generation	Line Drawing Abstraction Based on Line Importance Evaluation
Linear Time-Invariant (LTI) Modeling	On a Dissimilarity Metric for Analyzing Body Synergistic Coordination in Non-Periodic Motion
Lipreading	VCHFC: Visual-Content Hybrid Feature Cue Module for Lipreading
Local Salient Kernel	Enhancing Nvshu Recognition Based on Polarity-aware Linear Attention and Learnable Local Salient Kernel
Long-Short Joint motion chain	Multi-Granularity Feature Extraction Based on Long-Short Chains for Motion Retargeting
LoRA	StyleRegLoRA: An Improved Framework for SDXL LoRA Fine-tuning Towards Art Category Generation
Low-Frequency information	Veiled Diffusion: A Diffusion-Based Anti-Customization Adversarial Attack Method via Semantic Misalignment and Low-Frequency Information
Low-High Frequency Feature Decomposition	IMFDM: Improved Mamba-based Feature Decomposition Model for Multi-Modality Image Fusion
Low-light image enhancement	BWANet: A low-light image detail enhancement network with multi-scale large receptive fields Embedding Space Decomposition Meets Invertible Networks: A New Paradigm for Unpaired Low-Light Enhancement
M
Machine learning	Machine Learning Approach for Color Selection near Light/Dark Boundaries Considering Emotional Impressions Real-Time EEG-Based Fear Intensity Estimation for Virtual Reality Exposure Therapy Geometric Algebra-Based Time Series Reconstruction of Sea Level Variability – A Case Study Along the Northeast Pacific Coast (1993-2023)
Machining feature recognition	An Industrial Multi-Machining Feature Dataset and Contrastive Learning-based Network for Feature Recognition
Mamba Convolution	FusionCraft: A New Paradigm for Fine-Grained Multimodal Fashion Design Generation
Map representation alignment	TriAlign: Revisiting Deep Functional Map from Map Representation Alignment Perspectives
Material Appearance	Reproducing the Appearance of Metallic Materials by Capturing Long-Range Dependencies using Image-to-Image Translation Network with Vision Transformer
Material Point Method	Enhanced Material Point Method with Affine Projection Stabilizer for Efficient Hyperelastic Simulations
maximum flow	RegistrationBooster: Enhancing Rigid Registration Performance through Correspondence Refinement
Mechanism Theory	Geometric Algebra and Mechanism Theory
Medial Axis	Image Halftoning Using a Single Closed Non-self-intersecting Curve
Medical image registration	PCM-Net: A Hierarchical Medical Image Registration Framework Integrating Channel Adaptability and Multi-Scale Awareness
Medical Image Segmentation	RaEUNet: A Retentive and Efficient UNet for Medical Image Segmentation PLNet: Entropy-Guided Pseudo Label Refinement with Sensitivity-Specificity Enhancement for Medical Image Segmentation
Medical imaging	Graph Convolutional Networks for 3D Skeleton-Based Scoliosis Screening Using Gait Sequences Hypercomplexification of U-Net by Clifford Algebra Embeddings
Memory bank	Energy-guided Test-time Adaptation for Data Shifts in Multi-modal Perception
Memory Management	Boosting Memory Network for Video Object Segmentation in Complex Scenes
Memory Requirements	Geometric Algebra: An Overview About Different Implementation Representations and Memory Requirements
Mesh simplification	ImS: Implicit Shell for the Sandwich-Walled Space Surrounding Polygonal Meshes
Micro-Expression Recognition	AMNet: An Attention-Enhanced Multi-Branch Network for Micro-Expression Recognition Bimodal VIT Adaptive Cross-Fusion Micro-Expression Recognition Based on ECG-QRS Waves
Minimal surface energy	High-Quality Neural Surface Reconstruction from Unoriented Point Clouds via Multilevel Tensor Product B-spline Hash Encoding and Viscosity Regularization
Mirror detection	MDSAM: Intrinsic Cues Guided Segmentation for Mirror Detection
Modality-enhanced	Cross-Layer Feature Aggregation Object Detection Networks for Modality-enhanced UAV Images
Monncular reconstruction	Te3DFR: Texture-enabled 3D Face Reconstruction from Monocular Image via Self-supervised Learning
Monogenic quaternionic polynomials	Keynote: Normal Forms of Coordinate-Free Quaternionic Polynomials
Motion Decoder	A Two Stage Controllable Co-Speech Gesture Generation Method
Motion Features	MOT FCG++: Enhanced Representation of Spatio-temporal Motion and Appearance Features
Motion Information Enhancement	Interpretable Two-Stage Action Quality Assessment via 3D Human Pose Estimation and Dynamic Feature Alignment
Motion retargeting	Multi-Granularity Feature Extraction Based on Long-Short Chains for Motion Retargeting
Muiltiview synthesis	Latent Interpretation for Multi-View Face Synthesis across GAN and Diffusion via Conditional Reconstruction
Mult-Agents	MatLayerNet: A Multi-Agent-Based Method for Text-to-PBR Material Generation
Multi-Agent Learning	Multi-Agent Learning with Hierarchical Prompt for Efficient 3D Human Pose Estimation in Virtual Reality
Multi-agent system	MAS-KCL: Knowledge Component Graph Structure Learning with Large Language Model-based Agentic Workflow GA-VisAgent: A Multi-Agent Application for Code Generation and Visualization in Interactive Learning
Multi-dimensional unified	Self-Adaptive Geometric Updating Method for 3D Cadastral Parcels Based on Geometric Algebra
Multi-feature	An Industrial Multi-Machining Feature Dataset and Contrastive Learning-based Network for Feature Recognition
Multi-granularity feature	Multi-Granularity Feature Extraction Based on Long-Short Chains for Motion Retargeting
Multi-modal	MIGEdit: Multimodal Interactive Garment Editing
Multi-modal perception	Energy-guided Test-time Adaptation for Data Shifts in Multi-modal Perception
Multi-Modality	VCHFC: Visual-Content Hybrid Feature Cue Module for Lipreading
Multi-modality Image Fusion	IMFDM: Improved Mamba-based Feature Decomposition Model for Multi-Modality Image Fusion
Multi-scale	Scale-aware Guidance Network for SAR Ship Object Detection
Multi-scale Architecture	SCAU-Net: An Efficient Module for Multi-scale Feature Extraction and Aggregation in Video Super-Resolution
Multi-Scale Feature Extraction	Semantic-Orthogonal Multi-modal Attention Network for RGB-D Salient Object Detection
Multi-Scale Fusion	Enhancing Nvshu Recognition Based on Polarity-aware Linear Attention and Learnable Local Salient Kernel
Multi-scale Memory Reading	Boosting Memory Network for Video Object Segmentation in Complex Scenes
Multi-scale receptive field	BWANet: A low-light image detail enhancement network with multi-scale large receptive fields
Multi-scale reconstruction	UMan: Multi-Scale Feature Reconstruction and Super-Resolution for Single-Image 3D Human Modeling
multi-user	Obstacle Avoidance Strategy Based on Spatial Contraction for Multi-User Redirected Walking
Multi-View Diffusion Generation	UMan: Multi-Scale Feature Reconstruction and Super-Resolution for Single-Image 3D Human Modeling
Multi-view Stereo	DOMVS:Unsupervised Multi-View Stereo for Dealing With Occlusion Scenes
Multi-weather	Enhancing Small Object Detection in Aerial Images Under Multi-Weather Conditions Using Modified YOLO
Multidimensional data	Hypercomplexification of U-Net by Clifford Algebra Embeddings
Multilevel Monte Carlo	Multilevel Monte Carlo for Asymptotically Efficient Path Tracing
multimedia security	Privacy Image Secrecy Scheme Based on Chaos-Driven FSM and FQM
Multimodal	Bimodal VIT Adaptive Cross-Fusion Micro-Expression Recognition Based on ECG-QRS Waves WA-FDNet: A Unified Weight Adaptation Network for Multimodal Image Fusion and Object Detection Bearing Remaining Useful Life Prediction Using Multimodal Features by Balanced Optimization Between Time-series and Images A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images
Multimodal data	Hypercomplexification of U-Net by Clifford Algebra Embeddings
Multimodal Fashion Dataset	D^2-Diff: Controllable Fashion Image Generation with Disentangled Style and Content
Multimodal Generation	FusionCraft: A New Paradigm for Fine-Grained Multimodal Fashion Design Generation
Multimodal Learning	Dynamic Prompting and Cross-Modal Attention for Context-Aware Multimodal Emotion Recognition
Multimodal Trajectories	Scene-Enhanced Social Interpretable Movement Behavior for Multimodal Pedestrian Trajectory Prediction
multiplication table	Contemplating Susumu Okubo's Algebra of Quantum Color Dynamics
Multiscale discriminator	Face Sketch Synthesis via Sparse Spatial Channel Generators and Multi-Scale Discriminators
multispectral	A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images
Multiview-consistency	Building 3DGS Representation for Single Interested Object via Joint Segmentation-training Framework
Mutual Information	Distilling Complementary Information from Temporal Context for Enhancing Human Appearance in Human-Specific NeRF
N
Nadine	The Evolution of Digital Humans: Past, Present, and the Road Ahead
NeRF	Submodular-based View Selection for Low-Quality Points Rendering with Multi-Feature Point-based NeRF Dynamic voxel grid optimization for high-fidelity rgb-d supervised surface reconstruction
network · unsupervised	SEGNet: Shot-Flexible Exposure Guided Image Reconstruction Network
Neural Field	Neural-GASh: A CGA-Based Neural Radiance Prediction Pipeline for Real-Time Shading
Neural implicit representation	High-Quality Neural Surface Reconstruction from Unoriented Point Clouds via Multilevel Tensor Product B-spline Hash Encoding and Viscosity Regularization
Neural Network	Predicting and Optimizing Crowd Evacuations: An Explainable AI Approach Generating 3D fish motion skeleton via iterative optimization method and FishSkeletonNet Neural-GASh: A CGA-Based Neural Radiance Prediction Pipeline for Real-Time Shading
Neural networks	Hypercomplexification of U-Net by Clifford Algebra Embeddings Enhancing Vision Transformer for Fine-Grained Classification with Selective Attention Aggregation and Multi-Head Noise Suppression
Neural Radiance Fields	L2H-NeRF: Low- to High-Frequency-Guided NeRF for 3D Reconstruction With a Few Input Scenes
Neural Radiation Fields	EE-Head: Emotion Estimation for Precise Facial Expression in NeRF Head Avatars
Neural Rendering	Distilling Complementary Information from Temporal Context for Enhancing Human Appearance in Human-Specific NeRF Submodular-based View Selection for Low-Quality Points Rendering with Multi-Feature Point-based NeRF
Neural signed distance functions	RevolRecon:Neural Representation for Reconstructing Surface of Revolution
No-reference Image Quality Assessment	Enhancing the Transferability of Adversarial Examples against No-Reference Image Quality Assessment Models
Non-isometric 3D shape correspondence ·	EDiffNet: An Enhanced DiffusionNet for Non-isometric 3D Shape Correspondence and Matching
Non-rigid shape correspondence	TriAlign: Revisiting Deep Functional Map from Map Representation Alignment Perspectives
Normalization	Keynote: Normal Forms of Coordinate-Free Quaternionic Polynomials
Novel view synthesis	Distilling Complementary Information from Temporal Context for Enhancing Human Appearance in Human-Specific NeRF MC-Gaussian: 3D Gaussian Splatting with Multi-camera in Autonomous Driving
numerical simulation	Deep Learning-based Digital Twin for Real-time Fire Safety Management
Nvshu Recognition	Enhancing Nvshu Recognition Based on Polarity-aware Linear Attention and Learnable Local Salient Kernel
O
Object detection	WA-FDNet: A Unified Weight Adaptation Network for Multimodal Image Fusion and Object Detection EX-YOLO: Improve YOLOv11 to achieve efficient detection of small targets of drones
Object detection branch	An Improved Small Object Detection Method for Shuttlecock Activity Analysis
object detector	SDOD: Towards Reliable Object Detection under Diverse Rainy Conditions with Deraining and Mutual Learning
Object Interaction	Dynamic Translational Gains Manipulation for Tiny Object Interaction
Object Tracking	MOT FCG++: Enhanced Representation of Spatio-temporal Motion and Appearance Features
Occlusion mask	Multi-Scale Attention and Adaptive Self-Attention for Occlusion-Aware Depth Estimation in Light Field
Occlusion Robustness	Multi-Agent Learning with Hierarchical Prompt for Efficient 3D Human Pose Estimation in Virtual Reality
Offset Curve	Image Halftoning Using a Single Closed Non-self-intersecting Curve
Okubo algebra	Contemplating Susumu Okubo's Algebra of Quantum Color Dynamics
Open environment	A continuous test-time adaptation method for dynamic haze removal
Open-Source Tool	PeelMesh: Efficient Interactive Segmentation via Geodesic-Driven Dynamic Topological Updates
Open-vocabulary	OSH-Splat: Optimizable Semantic Hyperplanes for Enhanced 3D Language Feature Gaussian Splatting
Optical Flow	Learning Human-Object Interactions in Videos with Optical Flow
Optical Flow and Motion Feature	AMNet: An Attention-Enhanced Multi-Branch Network for Micro-Expression Recognition
Optimization	Turbulence Estimation in Smoke Simulation via Curvature-Based Image Features
Orthogonal Multi-Modal Mutual Attention	Semantic-Orthogonal Multi-modal Attention Network for RGB-D Salient Object Detection
outlier handling	ConDT: A 2D curve reconstruction algorithm based on a constrained-neighbor proximity graph
P
Pancreas segmentation	UNet-3D with Adaptive TverskyCE Loss for Pancreas Medical Image Segmentation
para-quaternions	Contemplating Susumu Okubo's Algebra of Quantum Color Dynamics
parallel processing architecture	Accelerating Error Diffusion Halftoning for High-Throughput Wide-Format Industrial Printing
Parameter estimation	Turbulence Estimation in Smoke Simulation via Curvature-Based Image Features
Parameter Identification	Keynote: Geometric Algebra in Electrical Engineering: A Comprehensive Review of Power Systems Applications
parameter-diminish fine-tuning	PDFT: Parameter-Diminish Fine-Tuning for Transformer-based Models
Parameter-effcient fine-tuning	PDFT: Parameter-Diminish Fine-Tuning for Transformer-based Models
Partial differential equation	Physics-Guided Deep Learning Framework with Attention for Image Denoising
Path Planning	Fuzzy Logic-Based Virtual Leading Path Planning for Autonomous Underwater Vehicles: An Evaluation Index Approach
Path tracing	Direct Coherent Ray Generation for Path Tracing
penetration	GartransNet: 3D garments animation via transmission optimized networks
Perception shifts	From Sci-Fi to Reality: Exploring Teenagers' Perceptions and Ideas of AI Robots
Perceptual Consistency	DOMVS:Unsupervised Multi-View Stereo for Dealing With Occlusion Scenes
Perceptual similarity	Video Sketching using Multi-domain Guidance and Implicit Encoding
perceptual study	Decoding Emotions: How Eye Features Influence Perception of Emotional Intensity in Virtual Characters
Phase-shifted fringes	A Novel Approach to Defocus Region Detection in Phase-Shifting Structured Light 3D Reconstruction
Physical simulation	Enhanced Material Point Method with Affine Projection Stabilizer for Efficient Hyperelastic Simulations
Physically based modeling	Adaptive Sampling for Interactive Simulation of Granular Material
physics optimization	PhysAvatar: Physically Plausible Avatar Generation from Sparse Tracking
Physics Simulation	Extending Implicit Density Projection for Multiphase Fluids
Physics-based simulation	Real-Time Immersive Haptic Sculpting with Elastoplastic Virtual Clay
Physics-guided deep models	Physics-Guided Deep Learning Framework with Attention for Image Denoising
Point annotation	Weakly Semi-supervised Classroom Teacher Visual Tracking by Single-point Annotations
Point Cloud	MIC-OPCC: Multi-Indexed Convolution model for Octree Point Cloud Compression Efficient Modeling of Long-Range Morphology for 3D Neuron Reconstruction from Electron Microscopy Images
Point Cloud classification	Task-adaptive Channel Attention Graph Network for Few-shot 3D Point Cloud Classification
Point Cloud Completion	Submodular-based View Selection for Low-Quality Points Rendering with Multi-Feature Point-based NeRF
point cloud registration	A Novel Registration Framework For Large-scale Point Clouds via Geometric Salience Computation RegistrationBooster: Enhancing Rigid Registration Performance through Correspondence Refinement
Point Clouds	Attention-Guided Self-Supervised Distinctive Region Detection in Point Clouds
Polarity-Aware	Enhancing Nvshu Recognition Based on Polarity-aware Linear Attention and Learnable Local Salient Kernel
Portrait Shadow Removal	PortraitFormer: Global Illumination Helps Portrait Shadow Removal
pose generation from sparse observations	PhysAvatar: Physically Plausible Avatar Generation from Sparse Tracking
Position Based Dynamics	Adaptive Sampling for Interactive Simulation of Granular Material
Post-hoc interpretability	Scale-aware Guidance Network for SAR Ship Object Detection
Power Flow Analysis	Keynote: Geometric Algebra in Electrical Engineering: A Comprehensive Review of Power Systems Applications
Power Systems	Keynote: Geometric Algebra in Electrical Engineering: A Comprehensive Review of Power Systems Applications
powers of Okubo units	Contemplating Susumu Okubo's Algebra of Quantum Color Dynamics
Pre-cleaning	PPVSR:Video Super-Resolution Reconstruction Algorithms Based on Progressive Processing
pre-train	A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images
Precomputed Radiance Transfer	Neural-GASh: A CGA-Based Neural Radiance Prediction Pipeline for Real-Time Shading
Prior Knowledge	Boosting Remote Semantic Segmentation Using Vision-and- language Foundation Model
procedural content generation	Exploring Procedural Content Generation of 3D City Scenes for 2D Semantic Segmentation
Programmable Gradient Information	PGI-ViMamba: A Robust Neural Network Architecture for Enhanced Small Target Detection Against Information Loss
Projection Method	Attention-enhanced 3D craniomaxillofacial anatomical landmark detection based on projection
Pseudo Label Optimization	PLNet: Entropy-Guided Pseudo Label Refinement with Sensitivity-Specificity Enhancement for Medical Image Segmentation
Pseudo-label denoising	Remote Sensing Cross-Domain Semantic Segmentation for Unknown Class Detection in Real-World Scenarios
Q
QR code	StencilQR: Connectivity-enhanced Fabricable QR Codes for Stencil
quantum computing	Notes on Quantum Computing over Complex Geometric Algebras with Split Signature
Quaternionic polynomials	Keynote: Normal Forms of Coordinate-Free Quaternionic Polynomials
R
Radiance Prediction	Neural-GASh: A CGA-Based Neural Radiance Prediction Pipeline for Real-Time Shading
RaEUNet	RaEUNet: A Retentive and Efficient UNet for Medical Image Segmentation
rainy weather	SDOD: Towards Reliable Object Detection under Diverse Rainy Conditions with Deraining and Mutual Learning
Ray tracing	Batch Specular Manifold Sampling for Caustics Rendering Multilevel Monte Carlo for Asymptotically Efficient Path Tracing
Real-time Detection	DL-DETR: Exploring the Future Directions of Fusion Between Dictionary Learning and DETR
Real-Time Interaction	Hi-Reco: High-Fidelity Real-Time Conversational Digital Humans
Real-time simulation	Adaptive Sampling for Interactive Simulation of Granular Material
Receptance Weighted Key Value Model	RainRWKV: A Deep RWKV Model for Video Deraining
Reconstruction	PPVSR:Video Super-Resolution Reconstruction Algorithms Based on Progressive Processing
redirected walking	Obstacle Avoidance Strategy Based on Spatial Contraction for Multi-User Redirected Walking
Relief Modeling	RelieFormer:End-to-End Bas Relief Generation via Transformer
Relighting	Generating Multi-Illumination Leaf Images through Single-Image Material Estimation for Robust Disease Recognition
Remaining useful life	Bearing Remaining Useful Life Prediction Using Multimodal Features by Balanced Optimization Between Time-series and Images
Remote sensing semantic segmentation	Remote Sensing Cross-Domain Semantic Segmentation for Unknown Class Detection in Real-World Scenarios
Rendering	Direct Coherent Ray Generation for Path Tracing Multilevel Monte Carlo for Asymptotically Efficient Path Tracing
Renewable Energy	Keynote: Geometric Algebra in Electrical Engineering: A Comprehensive Review of Power Systems Applications
Representation Learning	SpectralVAE: spectral variational autoencoder for 3D mesh representation learning
ResNet50	SigNet-TAM: Indian Sign Language Recognition with ResNet50-BiLSTM and Temporal Attention Mechanism
Retinex-based decomposition	Embedding Space Decomposition Meets Invertible Networks: A New Paradigm for Unpaired Low-Light Enhancement
Retrieval-augmented generation	MatLayerNet: A Multi-Agent-Based Method for Text-to-PBR Material Generation
RGB-D	Dynamic voxel grid optimization for high-fidelity rgb-d supervised surface reconstruction
Rigid loss function	Lightweight Image Super-Resolution Using Fine-Grained Feature Distillation in a Dense Residual U-Net
rigid transformation	RegistrationBooster: Enhancing Rigid Registration Performance through Correspondence Refinement
RMT	RaEUNet: A Retentive and Efficient UNet for Medical Image Segmentation
Robotic	MIC-OPCC: Multi-Indexed Convolution model for Octree Point Cloud Compression
Robustness and Security	DualShield: Dual-Layer Protection for Secure and Robust Stable Diffusion Steganography
Rotor Estimation	Symbolically Optimized Characteristic Multivector Rotor Estimation for 3D Point Cloud Registration
RT-DETR	DL-DETR: Exploring the Future Directions of Fusion Between Dictionary Learning and DETR
S
Saliency Detection	Attention-Guided Self-Supervised Distinctive Region Detection in Point Clouds
Salient Object Detection	Semantic-Orthogonal Multi-modal Attention Network for RGB-D Salient Object Detection BIDP: Brain-Inspired Dual-Process CNN-Transformer for Salient Object Detection
Sample-level evaluation	Generation of Realistic Synthetic ECG using Uncertainty-Aware Diffusion Model
Sampling	Batch Specular Manifold Sampling for Caustics Rendering
SAR	Scale-aware Guidance Network for SAR Ship Object Detection
Scale-aware	Scale-aware Guidance Network for SAR Ship Object Detection
Scaleless Sketch	Poll-Sketcher: Visual Exploration of Time-Varying Air Pollutant Data Based on Hand-drawn Sketches
Scene Information	Scene-Enhanced Social Interpretable Movement Behavior for Multimodal Pedestrian Trajectory Prediction
Science fiction films	From Sci-Fi to Reality: Exploring Teenagers' Perceptions and Ideas of AI Robots
Score distillation sampling	Text-driven High-quality 3D Human Generation via Variational Gradient Estimationl and Latent Reward Models
Sea level variability	Geometric Algebra-Based Time Series Reconstruction of Sea Level Variability – A Case Study Along the Northeast Pacific Coast (1993-2023)
Segment Anything Model	PDFT: Parameter-Diminish Fine-Tuning for Transformer-based Models
Segment Anything Model (SAM)	ZAP-2.5DSAM: Zero Additional Parameters Advancing 2.5D SAM Adaptation to 3D Tumor Segmentation MDSAM: Intrinsic Cues Guided Segmentation for Mirror Detection
Segmentation	GeloVec: Higher Dimensional Geometric Smoothing for Coherent Visual Feature Extraction in Image Segmentation
Selective Fusion	Small Object Detection Algorithm with Selective Fusion of Small Scale Features
Selective labeling	Efficient selective labeling strategies for enhanced few-shot 3D point cloud semantic segmentation
Self-Attention	Enhancing Vision Transformer for Fine-Grained Classification with Selective Attention Aggregation and Multi-Head Noise Suppression
Self-Calibrating Spatial Recursive Attention	Semantic-Orthogonal Multi-modal Attention Network for RGB-D Salient Object Detection
Self-supervised learning	Te3DFR: Texture-enabled 3D Face Reconstruction from Monocular Image via Self-supervised Learning
Self-supervised network	RevolRecon:Neural Representation for Reconstructing Surface of Revolution
Semantic Layout Generation	MELD: A Multi-Element Latent Diffusion Model for Urban Greenspace Layout Generation
Semantic misalignment	Veiled Diffusion: A Diffusion-Based Anti-Customization Adversarial Attack Method via Semantic Misalignment and Low-Frequency Information
semantic segmentation	A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images Exploring Procedural Content Generation of 3D City Scenes for 2D Semantic Segmentation
Semantic Token Sparsification	Semantic-Orthogonal Multi-modal Attention Network for RGB-D Salient Object Detection
Semantic-Assisted	Weakly Supervised Video Anomaly Detection via Temporal Dynamic Modeling and Semantic-Assisted Approach
Semi-cycle-GAN	Face Sketch Synthesis via Sparse Spatial Channel Generators and Multi-Scale Discriminators
Sensitivity-specificity Enhancement	PLNet: Entropy-Guided Pseudo Label Refinement with Sensitivity-Specificity Enhancement for Medical Image Segmentation
Sequence Fluid Image Generation	Sequential Fluid Image Generation Network Based on Spatio-Temporal Swin Transformer
shading removal	Cartoon Animation Shading Removal
Shadow Removal	Single Image Shadow Removal using 2D Signed Distance Field
Shallow Feature Map	Small Object Detection Algorithm with Selective Fusion of Small Scale Features
Shape analysis	ODFM: Orientation-Aware Dual-Branch Functional Maps for Unsupervised Non-rigid Shape Matching
Shape matching	ODFM: Orientation-Aware Dual-Branch Functional Maps for Unsupervised Non-rigid Shape Matching
Ship detection	Scale-aware Guidance Network for SAR Ship Object Detection
Shuttlecock tracking	An Improved Small Object Detection Method for Shuttlecock Activity Analysis
Sign Language Recognition	SigNet-TAM: Indian Sign Language Recognition with ResNet50-BiLSTM and Temporal Attention Mechanism
Similarity matching	EDiffNet: An Enhanced DiffusionNet for Non-isometric 3D Shape Correspondence and Matching
Single-object tracking	Weakly Semi-supervised Classroom Teacher Visual Tracking by Single-point Annotations
Sketch synthesis	Video Sketching using Multi-domain Guidance and Implicit Encoding
Small Intelligent sports analysis	An Improved Small Object Detection Method for Shuttlecock Activity Analysis
Small Object detection	Small Object Detection Algorithm with Selective Fusion of Small Scale Features PGI-ViMamba: A Robust Neural Network Architecture for Enhanced Small Target Detection Against Information Loss
Small-object detection	Enhancing Small Object Detection in Aerial Images Under Multi-Weather Conditions Using Modified YOLO
small-sized objects	EX-YOLO: Improve YOLOv11 to achieve efficient detection of small targets of drones
Smart Grids	Keynote: Geometric Algebra in Electrical Engineering: A Comprehensive Review of Power Systems Applications
SMPL-X Model	Enhancing Single-View 3D Clothed Human Reconstruction with Hybrid Prior Integration
Social Robot	The Evolution of Digital Humans: Past, Present, and the Road Ahead
Space-time Memory Network	Boosting Memory Network for Video Object Segmentation in Complex Scenes
Sparse Reconstruction	L2H-NeRF: Low- to High-Frequency-Guided NeRF for 3D Reconstruction With a Few Input Scenes
Sparse spatial channel generators	Face Sketch Synthesis via Sparse Spatial Channel Generators and Multi-Scale Discriminators
Sparse voxel octree	ImS: Implicit Shell for the Sandwich-Walled Space Surrounding Polygonal Meshes
SparseInst network	Reliable AI-Driven Decision Analysis of Ophthalmic Plastic Surgery Parameters with SparseInst Network
spatial contraction	Obstacle Avoidance Strategy Based on Spatial Contraction for Multi-User Redirected Walking
Spatial modeling	Multi-Granularity Feature Extraction Based on Long-Short Chains for Motion Retargeting
Spatial Reconstruction Multi-Scale Dilated Attention	YOLO-Pest A Model Design for Crop Pest Detection
Spatio-temporal Gated Mamba	Dual-Path Spatio-Temporal Mamba for Skeleton-Based Action Recognition
Spatiotemporal Modeling	AMNet: An Attention-Enhanced Multi-Branch Network for Micro-Expression Recognition
Spectral Analysis	SpectralVAE: spectral variational autoencoder for 3D mesh representation learning
SPH	Guiding Steady Fluid Flow with Terrain-Based Repulsive Forces
Spherical parameterizations	Bijective Spherical Parameterization via Stereographic Projection
Spherical Shell Intersections	Keynote: Conformal Geometric Algebra for Spherical Shell Intersections
split signature	Notes on Quantum Computing over Complex Geometric Algebras with Split Signature
Stable Diffusion	PG-VTON: Front-and-Back Garment Guided Panoramic Gaussian Virtual Try-On with Diffusion Modeling
State Space Model	LA-mUNet: An Efficient Hybrid CNN-Mamba Network with Lesion Attention for 3D Brain Tumor MRI Segmentation
State Space Sequence Models	Efficient Modeling of Long-Range Morphology for 3D Neuron Reconstruction from Electron Microscopy Images
Stencil Design	StencilQR: Connectivity-enhanced Fabricable QR Codes for Stencil
Stereographic projection	Bijective Spherical Parameterization via Stereographic Projection
Strike counting	An Improved Small Object Detection Method for Shuttlecock Activity Analysis
String Theory	Clifford(11,1) String Theory
strip pooling module	Reliable AI-Driven Decision Analysis of Ophthalmic Plastic Surgery Parameters with SparseInst Network
structural contexts	Exploring Structural Lines for Interior Floorplan Segmentation
Structural similarity · exposure guidance ·	SEGNet: Shot-Flexible Exposure Guided Image Reconstruction Network
Structured light 3D reconstruction	A Novel Approach to Defocus Region Detection in Phase-Shifting Structured Light 3D Reconstruction
Structured Occlusion	DOMVS:Unsupervised Multi-View Stereo for Dealing With Occlusion Scenes
Style generation	StyleRegLoRA: An Improved Framework for SDXL LoRA Fine-tuning Towards Art Category Generation
Style Transfer	Feature Replacement in Gaussian Splatting for 3D Stylization Dynamic Style-Adaptive Image Transformation Network
Style-Content Disentanglement	D^2-Diff: Controllable Fashion Image Generation with Disentangled Style and Content
subalgebras	Contemplating Susumu Okubo's Algebra of Quantum Color Dynamics
Submodular Optimization	Submodular-based View Selection for Low-Quality Points Rendering with Multi-Feature Point-based NeRF
Super resolution	UMan: Multi-Scale Feature Reconstruction and Super-Resolution for Single-Image 3D Human Modeling
Super-resolution	Coordinate-Aware Implicit Image Function for Arbitrary-Scale Image Super-Resolution
Superpixel hierarchies	Few-shot Medical Image Segmentation via Query Transformation Learning
Superpixel label generation	Adaptive Box-Level Supervision with Superpixel Shape Guidance for Ultrasound Image Segmentation
Surface of revolution	RevolRecon:Neural Representation for Reconstructing Surface of Revolution
Surface reconstruction	High-Quality Neural Surface Reconstruction from Unoriented Point Clouds via Multilevel Tensor Product B-spline Hash Encoding and Viscosity Regularization RevolRecon:Neural Representation for Reconstructing Surface of Revolution Dynamic voxel grid optimization for high-fidelity rgb-d supervised surface reconstruction
Swin Transformer	Sequential Fluid Image Generation Network Based on Spatio-Temporal Swin Transformer
Symmetric Matching	Intrinsic Reflective Symmetry Axis Curve Generation for Meshes
Symmetric Sampling	Intrinsic Reflective Symmetry Axis Curve Generation for Meshes
Synthetic	The Power of Geometric-Algebra Rotation Composition for Adaptive Filtering
T
Teenagers	From Sci-Fi to Reality: Exploring Teenagers' Perceptions and Ideas of AI Robots
Temporal Attention	SigNet-TAM: Indian Sign Language Recognition with ResNet50-BiLSTM and Temporal Attention Mechanism
Temporal consistency	Video Sketching using Multi-domain Guidance and Implicit Encoding
Temporal Dynamic Modeling	Weakly Supervised Video Anomaly Detection via Temporal Dynamic Modeling and Semantic-Assisted Approach
Tensor-product B-splines	ImS: Implicit Shell for the Sandwich-Walled Space Surrounding Polygonal Meshes
Terrain	Guiding Steady Fluid Flow with Terrain-Based Repulsive Forces TerraFusion: Joint Generation of Terrain Shape and Texture Using Latent Diffusion Models
Test-time adaptation	A continuous test-time adaptation method for dynamic haze removal
Test-time adaption	Energy-guided Test-time Adaptation for Data Shifts in Multi-modal Perception
Text-driven	Text-driven High-quality 3D Human Generation via Variational Gradient Estimationl and Latent Reward Models
Text-guided texturing	MatLayerNet: A Multi-Agent-Based Method for Text-to-PBR Material Generation
Text-to-image generation	StyleRegLoRA: An Improved Framework for SDXL LoRA Fine-tuning Towards Art Category Generation
Texture Optimization	Texture and Geometry Optimization for 3D Reconstruction
The light/dark boundary line	Machine Learning Approach for Color Selection near Light/Dark Boundaries Considering Emotional Impressions
Time series	Geometric Algebra-Based Time Series Reconstruction of Sea Level Variability – A Case Study Along the Northeast Pacific Coast (1993-2023) Poll-Sketcher: Visual Exploration of Time-Varying Air Pollutant Data Based on Hand-drawn Sketches
Tiny Objects	Dynamic Translational Gains Manipulation for Tiny Object Interaction
transfer learning	A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images
Transferability	Enhancing the Transferability of Adversarial Examples against No-Reference Image Quality Assessment Models
Transformation Generators	Geometric Algebra for Quadrics
Transformer	An Asymmetric Calibrated Transformer Network for Underwater Image Restoration Physics-Guided Deep Learning Framework with Attention for Image Denoising RelieFormer:End-to-End Bas Relief Generation via Transformer CoFormer:Coupling Attentive Model for Visual Sentiment Analysis with Hierarchical Emotion Loss A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images
Triplane Feature	SemanticAvatar: Human Surface Reconstruction Based on Semantically Consistent Biplane Features
Truncated Network	A Visual Self-attention Mechanism Facial Expression Recognition Network beyond Convnext
Tumor Segmentation	ZAP-2.5DSAM: Zero Additional Parameters Advancing 2.5D SAM Adaptation to 3D Tumor Segmentation
Tversky loss	UNet-3D with Adaptive TverskyCE Loss for Pancreas Medical Image Segmentation
U
U-Net Architecture	SWAN: A Synergistic Wavelet Attention Network for Enhanced Underwater Image Enhancement
U-net network	Lightweight Image Super-Resolution Using Fine-Grained Feature Distillation in a Dense Residual U-Net
ultra-high-definition	An Effective Wavelet Neural Network for Ultra-High-Definition Image Deraining
Ultrasound image segmentation	Adaptive Box-Level Supervision with Superpixel Shape Guidance for Ultrasound Image Segmentation
Uncertainty-Aware	Generation of Realistic Synthetic ECG using Uncertainty-Aware Diffusion Model
Underwater image enhancement	DTKD-UIE: Underwater Image Enhancement based on Dual Teacher knowledge distillation SWAN: A Synergistic Wavelet Attention Network for Enhanced Underwater Image Enhancement
Underwater image restoration	An Asymmetric Calibrated Transformer Network for Underwater Image Restoration
UNet-3D	UNet-3D with Adaptive TverskyCE Loss for Pancreas Medical Image Segmentation
Unified model	UTFusion: A General Image Fusion Framework with a Unified Transformer
Unknown class detection	Remote Sensing Cross-Domain Semantic Segmentation for Unknown Class Detection in Real-World Scenarios
unmanned aerial vehicle (UAV) image	Cross-Layer Feature Aggregation Object Detection Networks for Modality-enhanced UAV Images
Unoriented Points	3D Reconstructions from Unoriented Points: Recent Advances and Emerging Trends
Unsupervised domain adaptation	Remote Sensing Cross-Domain Semantic Segmentation for Unknown Class Detection in Real-World Scenarios
Unsupervised Learning	CADGCL: Unsupervised Retrieval of CAD Models Via Boundary Representations DOMVS:Unsupervised Multi-View Stereo for Dealing With Occlusion Scenes
Unsupervised registration	PCM-Net: A Hierarchical Medical Image Registration Framework Integrating Channel Adaptability and Multi-Scale Awareness
Urban layout regeneration	GUM-DiT: A Foundation Model for Generating Urban Morphological Layouts
Urban Modeling	MELD: A Multi-Element Latent Diffusion Model for Urban Greenspace Layout Generation
V
Valid region mask	A Novel Approach to Defocus Region Detection in Phase-Shifting Structured Light 3D Reconstruction
Variable-speed Sampling	VS-DSN: Variable-Speed Dual-Stream Network for Continuous Sign Language Recognition
Video Anomaly Detection	Weakly Supervised Video Anomaly Detection via Temporal Dynamic Modeling and Semantic-Assisted Approach
Video Deraining	RainRWKV: A Deep RWKV Model for Video Deraining
Video Frame Interpolation	Transforming Time and Space: Efficient Video Super-Resolution with Hybrid Attention and Deformable Transformers
Video Object Segmentation	Boosting Memory Network for Video Object Segmentation in Complex Scenes
Video processing	Video Sketching using Multi-domain Guidance and Implicit Encoding
Video Super Resolution	Transforming Time and Space: Efficient Video Super-Resolution with Hybrid Attention and Deformable Transformers SCAU-Net: An Efficient Module for Multi-scale Feature Extraction and Aggregation in Video Super-Resolution
Video super-resolution	PPVSR:Video Super-Resolution Reconstruction Algorithms Based on Progressive Processing
Video-Language Learning	Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions
virtual avatar driving	FaceCapGes: Real-Time Frame-by-Frame Gesture Generation from Audio, Facial Capture, and Head Pose
Virtual characters	Decoding Emotions: How Eye Features Influence Perception of Emotional Intensity in Virtual Characters
Virtual Human Avatar	GenericAvatar: Generic Human Modeling from Monocular Video Based on Mesh-guided Gaussians
Virtual Leader	Fuzzy Logic-Based Virtual Leading Path Planning for Autonomous Underwater Vehicles: An Evaluation Index Approach
Virtual Reality	Multi-Agent Learning with Hierarchical Prompt for Efficient 3D Human Pose Estimation in Virtual Reality Dynamic Translational Gains Manipulation for Tiny Object Interaction Obstacle Avoidance Strategy Based on Spatial Contraction for Multi-User Redirected Walking MIC-OPCC: Multi-Indexed Convolution model for Octree Point Cloud Compression Real-Time EEG-Based Fear Intensity Estimation for Virtual Reality Exposure Therapy
virtual try-on	PG-VTON: Front-and-Back Garment Guided Panoramic Gaussian Virtual Try-On with Diffusion Modeling Advancements and Challenges of Deep Learning in Virtual Try-On: A Comprehensive Review
Viscosity regularization	High-Quality Neural Surface Reconstruction from Unoriented Point Clouds via Multilevel Tensor Product B-spline Hash Encoding and Viscosity Regularization
Vision Mamba	PGI-ViMamba: A Robust Neural Network Architecture for Enhanced Small Target Detection Against Information Loss
Vision Transformer	ENViT-FAS: ENViT with Attack-Oriented Augmentation for Domain-Generalized Face Anti-Spoofing Reproducing the Appearance of Metallic Materials by Capturing Long-Range Dependencies using Image-to-Image Translation Network with Vision Transformer TADT: Task-aligned Deep Tracking DDVT: Dynamic Dual-level Vision Transformer Fusion Network for Answer Grounding in Visual Question Answering Enhancing Vision Transformer for Fine-Grained Classification with Selective Attention Aggregation and Multi-Head Noise Suppression SWAN: A Synergistic Wavelet Attention Network for Enhanced Underwater Image Enhancement
Vision Transformers	Hybrid-SANet: Hybrid Self-Attention Transformer for Efficient Image Super-Resolution
Visual Query	Poll-Sketcher: Visual Exploration of Time-Varying Air Pollutant Data Based on Hand-drawn Sketches
Visual question answering	DDVT: Dynamic Dual-level Vision Transformer Fusion Network for Answer Grounding in Visual Question Answering
Visual Self-attention Mechanism	A Visual Self-attention Mechanism Facial Expression Recognition Network beyond Convnext
Visual sentiment analysis	CoFormer:Coupling Attentive Model for Visual Sentiment Analysis with Hierarchical Emotion Loss
visual state-space model · convolutional neural	SEGNet: Shot-Flexible Exposure Guided Image Reconstruction Network
Visual tracking	ViT-BF: Vision Transformer with Border-aware Features for Visual Tracking TADT: Task-aligned Deep Tracking
Visual Transformer	Bimodal VIT Adaptive Cross-Fusion Micro-Expression Recognition Based on ECG-QRS Waves
Volume visualization	Enhancing INR-based Super-Resolution Performance in Scientific Visualization via a Priori and a Posteriori Constraints
Vorticity confinement	Turbulence Estimation in Smoke Simulation via Curvature-Based Image Features
W
Water Flow	Guiding Steady Fluid Flow with Terrain-Based Repulsive Forces
wavelet domain	Cross-Layer Feature Aggregation Object Detection Networks for Modality-enhanced UAV Images
Wavelet Transform	An Effective Wavelet Neural Network for Ultra-High-Definition Image Deraining Hybrid-SANet: Hybrid Self-Attention Transformer for Efficient Image Super-Resolution
Weakly supervised learning	Weakly Supervised Video Anomaly Detection via Temporal Dynamic Modeling and Semantic-Assisted Approach Weakly Semi-supervised Classroom Teacher Visual Tracking by Single-point Annotations
Web3D	Optimisation of Web-Edge-Cloud Intelligent Collaborative Rendering System For Dynamic Web3D Scenes
Wrapped phase	A Novel Approach to Defocus Region Detection in Phase-Shifting Structured Light 3D Reconstruction
X
XPBD Framework	Prototype XR Elastodynamics System for Disaster Medical Response
XR System	Prototype XR Elastodynamics System for Disaster Medical Response
Y
YOLO	Enhancing Small Object Detection in Aerial Images Under Multi-Weather Conditions Using Modified YOLO
YOLOv11	YOLO-Pest A Model Design for Crop Pest Detection EX-YOLO: Improve YOLOv11 to achieve efficient detection of small targets of drones
Z
Zero Additional Parameters (ZAP)	ZAP-2.5DSAM: Zero Additional Parameters Advancing 2.5D SAM Adaptation to 3D Tumor Segmentation
Zero-knowledge proof	A Privacy-preserving Collaborative 3D Design Framework for Copyright Protection

Disclaimer | Powered by EasyChair Smart Program