Days: Monday, July 14th Tuesday, July 15th Wednesday, July 16th Thursday, July 17th Friday, July 18th
View this program: with abstractssession overviewtalk overview
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 10:50 | Keynote: Normal Forms of Coordinate-Free Quaternionic Polynomials (abstract) |
| 11:15 | Geometric Algebra for Quadrics (abstract) |
| 11:30 | Explicit Formula for Inverse and Determinant in Geometric Algebras over Seven-dimensional Vector Spaces (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 11:45 | Symbolically Optimized Characteristic Multivector Rotor Estimation for 3D Point Cloud Registration (abstract) |
| 12:00 | GeloVec: Higher Dimensional Geometric Smoothing for Coherent Visual Feature Extraction in Image Segmentation (abstract) |
| 12:15 | On a Dissimilarity Metric for Analyzing Body Synergistic Coordination in Non-Periodic Motion (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 13:45 | Generative GeoSpatial Artificial Intelligence with Geometric Algebra |
| 14:00 | Geometric Algebra-Based Time Series Reconstruction of Sea Level Variability – A Case Study Along the Northeast Pacific Coast (1993-2023) (abstract) |
| 14:15 | Self-Adaptive Geometric Updating Method for 3D Cadastral Parcels Based on Geometric Algebra (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 14:30 | Clifford(11,1) String Theory |
| 14:45 | A Geometric Algebra Approach to Coincidence Site Lattices |
| 15:00 | Notes on Quantum Computing over Complex Geometric Algebras with Split Signature (abstract) |
| 15:15 | Contemplating Susumu Okubo's Algebra of Quantum Color Dynamics (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 16:00 | Keynote: Geometric Algebra in Electrical Engineering: A Comprehensive Review of Power Systems Applications (abstract) |
| 16:25 | Neural-GASh: A CGA-Based Neural Radiance Prediction Pipeline for Real-Time Shading (abstract) |
| 16:40 | Geometric Algebra and Mechanism Theory |
| 16:55 | Geometric Algebra: An Overview About Different Implementation Representations and Memory Requirements |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 17:10 | Hypercomplexification of U-Net by Clifford Algebra Embeddings (abstract) |
| 17:25 | Geometric Algebra for Cryptography and Artificial Intelligence: Demonstrating Concrete Performance and Expressiveness Advantages |
| 17:40 | GA-VisAgent: A Multi-Agent Application for Code Generation and Visualization in Interactive Learning (abstract) |
| 17:55 | Coordinate Free Circular Splines |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
View this program: with abstractssession overviewtalk overview
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 09:00 | The Evolution of Digital Humans: Past, Present, and the Road Ahead |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 09:30 | Towards Generative Filming: Progress and Challenges |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 11:00 | Batch Specular Manifold Sampling for Caustics Rendering (abstract) |
| 11:15 | Distilling Complementary Information from Temporal Context for Enhancing Human Appearance in Human-Specific NeRF (abstract) |
| 11:30 | Attention-Guided Self-Supervised Distinctive Region Detection in Point Clouds (abstract) |
| 11:45 | Energy-guided Test-time Adaptation for Data Shifts in Multi-modal Perception (abstract) |
| 12:00 | Bijective Spherical Parameterization via Stereographic Projection (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 11:00 | Dynamic voxel grid optimization for high-fidelity rgb-d supervised surface reconstruction (abstract) |
| 11:15 | MOT FCG++: Enhanced Representation of Spatio-temporal Motion and Appearance Features (abstract) |
| 11:30 | Attention-enhanced 3D craniomaxillofacial anatomical landmark detection based on projection (abstract) |
| 11:45 | SWAN: A Synergistic Wavelet Attention Network for Enhanced Underwater Image Enhancement (abstract) |
| 12:00 | MDSAM: Intrinsic Cues Guided Segmentation for Mirror Detection (abstract) |
Zoom Link: https://us06web.zoom.us/j/82346226482?pwd=Rwc3dmFUMa4UZ7qcAcfcsBPjJ7baXv.1 Meeting ID: 823 4622 6482 Passcode: CGI2025
| 11:00 | Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions (abstract) |
| 11:15 | Dynamic Prompting and Cross-Modal Attention for Context-Aware Multimodal Emotion Recognition (abstract) |
| 11:30 | UNet-3D with Adaptive TverskyCE Loss for Pancreas Medical Image Segmentation (abstract) |
| 11:45 | Building 3DGS Representation for Single Interested Object via Joint Segmentation-training Framework (abstract) |
| 12:00 | Poll-Sketcher: Visual Exploration of Time-Varying Air Pollutant Data Based on Hand-drawn Sketches (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 13:30 | An Asymmetric Calibrated Transformer Network for Underwater Image Restoration (abstract) |
| 13:45 | Instance-guided Cartoon Editing with a Curated Large-scale Dataset (abstract) |
| 14:00 | Locality-Preserving Free-Form Deformation (abstract) |
| 14:15 | Direct Coherent Ray Generation for Path Tracing (abstract) |
| 14:30 | Submodular-based View Selection for Low-Quality Points Rendering with Multi-Feature Point-based NeRF (abstract) |
| 14:45 | MAS-KCL: Knowledge Component Graph Structure Learning with Large Language Model-based Agentic Workflow (abstract) |
| 15:00 | AMNet: An Attention-Enhanced Multi-Branch Network for Micro-Expression Recognition (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 13:30 | PG-VTON: Front-and-Back Garment Guided Panoramic Gaussian Virtual Try-On with Diffusion Modeling (abstract) |
| 13:45 | Towards Extended Reality in Emergency Response: Guidelines and Challenges for First Responder Friendly Augmented Interfaces (abstract) |
| 14:00 | Predicting and Optimizing Crowd Evacuations: An Explainable AI Approach (abstract) |
| 14:15 | Adaptive Sampling for Interactive Simulation of Granular Material (abstract) |
| 14:30 | Dynamic Translational Gains Manipulation for Tiny Object Interaction (abstract) |
| 14:45 | Text-driven High-quality 3D Human Generation via Variational Gradient Estimationl and Latent Reward Models (abstract) |
Zoom Link: https://us06web.zoom.us/j/82346226482?pwd=Rwc3dmFUMa4UZ7qcAcfcsBPjJ7baXv.1 Meeting ID: 823 4622 6482 Passcode: CGI2025
| 13:30 | PPVSR:Video Super-Resolution Reconstruction Algorithms Based on Progressive Processing (abstract) |
| 13:45 | Reliable AI-Driven Decision Analysis of Ophthalmic Plastic Surgery Parameters with SparseInst Network (abstract) |
| 14:00 | DTKD-UIE: Underwater Image Enhancement based on Dual Teacher knowledge distillation (abstract) |
| 14:15 | An Improved Small Object Detection Method for Shuttlecock Activity Analysis (abstract) |
| 14:30 | PGI-ViMamba: A Robust Neural Network Architecture for Enhanced Small Target Detection Against Information Loss (abstract) |
| 14:45 | Hybrid-SANet: Hybrid Self-Attention Transformer for Efficient Image Super-Resolution (abstract) |
| 15:00 | PCM-Net: A Hierarchical Medical Image Registration Framework Integrating Channel Adaptability and Multi-Scale Awareness (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 15:45 | Real-Time Immersive Haptic Sculpting with Elastoplastic Virtual Clay (abstract) |
| 16:00 | SemanticAvatar: Human Surface Reconstruction Based on Semantically Consistent Biplane Features (abstract) |
| 16:15 | GenericAvatar: Generic Human Modeling from Monocular Video Based on Mesh-guided Gaussians (abstract) |
| 16:30 | EE-Head: Emotion Estimation for Precise Facial Expression in NeRF Head Avatars (abstract) |
| 16:45 | PhysAvatar: Physically Plausible Avatar Generation from Sparse Tracking (abstract) |
| 17:00 | Malicious Manipulation of Incident Light: Enabling Adversarial Relighting Attack with Physical Interpretability (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 15:45 | Decoding Emotions: How Eye Features Influence Perception of Emotional Intensity in Virtual Characters (abstract) |
| 16:00 | ODFM: Orientation-Aware Dual-Branch Functional Maps for Unsupervised Non-rigid Shape Matching (abstract) |
| 16:15 | MIC-OPCC: Multi-Indexed Convolution model for Octree Point Cloud Compression (abstract) |
| 16:30 | A Visual Self-attention Mechanism Facial Expression Recognition Network beyond Convnext (abstract) |
| 16:45 | Efficient Modeling of Long-Range Morphology for 3D Neuron Reconstruction from Electron Microscopy Images (abstract) |
| 17:00 | Obstacle Avoidance Strategy Based on Spatial Contraction for Multi-User Redirected Walking (abstract) |
Zoom Link: https://us06web.zoom.us/j/82346226482?pwd=Rwc3dmFUMa4UZ7qcAcfcsBPjJ7baXv.1 Meeting ID: 823 4622 6482 Passcode: CGI2025
| 15:45 | Dynamic Style-Adaptive Image Transformation Network (abstract) |
| 16:00 | A continuous test-time adaptation method for dynamic haze removal (abstract) |
| 16:15 | Bearing Remaining Useful Life Prediction Using Multimodal Features by Balanced Optimization Between Time-series and Images (abstract) |
| 16:30 | Optimisation of Web-Edge-Cloud Intelligent Collaborative Rendering System For Dynamic Web3D Scenes (abstract) |
| 16:45 | Image Halftoning Using a Single Closed Non-self-intersecting Curve (abstract) |
| 17:00 | Towards Culturally Aware AI: Quantified Evaluation of Relevance and Similarity in AI-Generated Images (abstract) |
View this program: with abstractssession overviewtalk overview
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 10:25 | SelfAge: Personalized Facial Age Transformation Using Self-reference Images (abstract) |
| 10:40 | Enhanced Material Point Method with Affine Projection Stabilizer for Efficient Hyperelastic Simulations (abstract) |
| 10:55 | CADGCL: Unsupervised Retrieval of CAD Models Via Boundary Representations (abstract) |
| 11:10 | From Sci-Fi to Reality: Exploring Teenagers' Perceptions and Ideas of AI Robots (abstract) |
| 11:25 | HumanIR-MGI: Human Inverse Rendering via Jointly Optimizing Geometry, Material, and Illumination (abstract) |
| 11:40 | Deep Learning-based Digital Twin for Real-time Fire Safety Management (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 10:25 | Generation of Realistic Synthetic ECG using Uncertainty-Aware Diffusion Model (abstract) |
| 10:40 | Remote Sensing Cross-Domain Semantic Segmentation for Unknown Class Detection in Real-World Scenarios (abstract) |
| 10:55 | Efficient Document Shadow Removal with Contrast-Aware Guidance (abstract) |
| 11:10 | Line Drawing Abstraction Based on Line Importance Evaluation (abstract) |
| 11:25 | Cartoon Animation Shading Removal (abstract) |
| 11:40 | SpectralVAE: spectral variational autoencoder for 3D mesh representation learning (abstract) |
Zoom Link: https://us06web.zoom.us/j/82346226482?pwd=Rwc3dmFUMa4UZ7qcAcfcsBPjJ7baXv.1 Meeting ID: 823 4622 6482 Passcode: CGI2025
| 10:25 | Cross-Layer Feature Aggregation Object Detection Networks for Modality-enhanced UAV Images (abstract) |
| 10:40 | Weakly Semi-supervised Classroom Teacher Visual Tracking by Single-point Annotations (abstract) |
| 10:55 | RegistrationBooster: Enhancing Rigid Registration Performance through Correspondence Refinement (abstract) |
| 11:10 | Face Sketch Synthesis via Sparse Spatial Channel Generators and Multi-Scale Discriminators (abstract) |
| 11:25 | Enhancing the Transferability of Adversarial Examples against No-Reference Image Quality Assessment Models (abstract) |
| 11:40 | Exploring Procedural Content Generation of 3D City Scenes for 2D Semantic Segmentation (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 13:30 | Privacy Image Secrecy Scheme Based on Chaos-Driven FSM and FQM (abstract) |
| 13:45 | Geometry Guidance Diffusion Image Morphing with Large Shape Difference (abstract) |
| 14:00 | RainRWKV: A Deep RWKV Model for Video Deraining (abstract) |
| 14:15 | Single Image Shadow Removal using 2D Signed Distance Field (abstract) |
| 14:30 | Adaptive Box-Level Supervision with Superpixel Shape Guidance for Ultrasound Image Segmentation (abstract) |
| 14:45 | SEGNet: Shot-Flexible Exposure Guided Image Reconstruction Network (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 13:30 | PortraitFormer: Global Illumination Helps Portrait Shadow Removal (abstract) |
| 13:45 | UTFusion: A General Image Fusion Framework with a Unified Transformer (abstract) |
| 14:00 | DDVT: Dynamic Dual-level Vision Transformer Fusion Network for Answer Grounding in Visual Question Answering (abstract) |
| 14:15 | MIGEdit: Multimodal Interactive Garment Editing (abstract) |
| 14:30 | LA-mUNet: An Efficient Hybrid CNN-Mamba Network with Lesion Attention for 3D Brain Tumor MRI Segmentation (abstract) |
| 14:45 | Scale-aware Guidance Network for SAR Ship Object Detection (abstract) |
Zoom Link: https://us06web.zoom.us/j/82346226482?pwd=Rwc3dmFUMa4UZ7qcAcfcsBPjJ7baXv.1 Meeting ID: 823 4622 6482 Passcode: CGI2025
| 13:30 | Small Object Detection Algorithm with Selective Fusion of Small Scale Features (abstract) |
| 13:45 | VCHFC: Visual-Content Hybrid Feature Cue Module for Lipreading (abstract) |
| 14:00 | Multi-Scale Attention and Adaptive Self-Attention for Occlusion-Aware Depth Estimation in Light Field (abstract) |
| 14:15 | UMan: Multi-Scale Feature Reconstruction and Super-Resolution for Single-Image 3D Human Modeling (abstract) |
| 14:30 | FusionCraft: A New Paradigm for Fine-Grained Multimodal Fashion Design Generation (abstract) |
| 14:45 | An Effective Wavelet Neural Network for Ultra-High-Definition Image Deraining (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 15:40 | RevolRecon:Neural Representation for Reconstructing Surface of Revolution (abstract) |
| 15:55 | High-Quality Neural Surface Reconstruction from Unoriented Point Clouds via Multilevel Tensor Product B-spline Hash Encoding and Viscosity Regularization (abstract) |
| 16:10 | ImS: Implicit Shell for the Sandwich-Walled Space Surrounding Polygonal Meshes (abstract) |
| 16:25 | ZAP-2.5DSAM: Zero Additional Parameters Advancing 2.5D SAM Adaptation to 3D Tumor Segmentation (abstract) |
| 16:40 | TriAlign: Revisiting Deep Functional Map from Map Representation Alignment Perspectives (abstract) |
| 16:55 | Efficient selective labeling strategies for enhanced few-shot 3D point cloud semantic segmentation (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 15:40 | An Industrial Multi-Machining Feature Dataset and Contrastive Learning-based Network for Feature Recognition (abstract) |
| 15:55 | IG-Diff: Complex Night Scene Restoration with Illumination-Guided Diffusion Model (abstract) |
| 16:10 | DualShield: Dual-Layer Protection for Secure and Robust Stable Diffusion Steganography (abstract) |
| 16:25 | Accelerating Error Diffusion Halftoning for High-Throughput Wide-Format Industrial Printing (abstract) |
| 16:40 | A Novel Registration Framework For Large-scale Point Clouds via Geometric Salience Computation (abstract) |
| 16:55 | Hi-Reco: High-Fidelity Real-Time Conversational Digital Humans (abstract) |
Zoom Link: https://us06web.zoom.us/j/82346226482?pwd=Rwc3dmFUMa4UZ7qcAcfcsBPjJ7baXv.1 Meeting ID: 823 4622 6482 Passcode: CGI2025
| 15:40 | MC-Gaussian: 3D Gaussian Splatting with Multi-camera in Autonomous Driving (abstract) |
| 15:55 | EDiffNet: An Enhanced DiffusionNet for Non-isometric 3D Shape Correspondence and Matching (abstract) |
| 16:10 | Enhancing INR-based Super-Resolution Performance in Scientific Visualization via a Priori and a Posteriori Constraints (abstract) |
| 16:25 | Enhancing Single-View 3D Clothed Human Reconstruction with Hybrid Prior Integration (abstract) |
| 16:40 | VS-DSN: Variable-Speed Dual-Stream Network for Continuous Sign Language Recognition (abstract) |
| 16:55 | Enhancing Nvshu Recognition Based on Polarity-aware Linear Attention and Learnable Local Salient Kernel (abstract) |
View this program: with abstractssession overviewtalk overview
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 09:15 | 3D Reconstructions from Unoriented Points: Recent Advances and Emerging Trends |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 10:40 | A Two Stage Controllable Co-Speech Gesture Generation Method (abstract) |
| 10:55 | Multi-Agent Learning with Hierarchical Prompt for Efficient 3D Human Pose Estimation in Virtual Reality (abstract) |
| 11:10 | Turbulence Estimation in Smoke Simulation via Curvature-Based Image Features (abstract) |
| 11:25 | Prototype XR Elastodynamics System for Disaster Medical Response (abstract) |
| 11:40 | Person-In-Situ: Scene-Consistent Human Image Insertion with Occlusion-Aware Pose Control (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 10:40 | StencilQR: Connectivity-enhanced Fabricable QR Codes for Stencil (abstract) |
| 10:55 | Recognize Me If You Can: Two-stream Adversarial Transfer for Facial Privacy Protection using Fine-grained Makeup (abstract) |
| 11:10 | Transforming Time and Space: Efficient Video Super-Resolution with Hybrid Attention and Deformable Transformers (abstract) |
| 11:25 | Exploring Structural Lines for Interior Floorplan Segmentation (abstract) |
| 11:40 | OSH-Splat: Optimizable Semantic Hyperplanes for Enhanced 3D Language Feature Gaussian Splatting (abstract) |
Zoom Link: https://us06web.zoom.us/j/82346226482?pwd=Rwc3dmFUMa4UZ7qcAcfcsBPjJ7baXv.1 Meeting ID: 823 4622 6482 Passcode: CGI2025
| 10:40 | BWANet: A low-light image detail enhancement network with multi-scale large receptive fields (abstract) |
| 10:55 | Guiding Steady Fluid Flow with Terrain-Based Repulsive Forces (abstract) |
| 11:10 | Knowledge Graph Completion by Integrating Local and Global Features (abstract) |
| 11:25 | TerraFusion: Joint Generation of Terrain Shape and Texture Using Latent Diffusion Models (abstract) |
| 11:40 | Bimodal VIT Adaptive Cross-Fusion Micro-Expression Recognition Based on ECG-QRS Waves (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 13:30 | PDFT: Parameter-Diminish Fine-Tuning for Transformer-based Models (abstract) |
| 13:45 | Dual-Path Spatio-Temporal Mamba for Skeleton-Based Action Recognition (abstract) |
| 14:00 | Boosting Memory Network for Video Object Segmentation in Complex Scenes (abstract) |
| 14:15 | ViT-BF: Vision Transformer with Border-aware Features for Visual Tracking (abstract) |
| 14:30 | Physics-Guided Deep Learning Framework with Attention for Image Denoising (abstract) |
| 14:45 | Interpretable Two-Stage Action Quality Assessment via 3D Human Pose Estimation and Dynamic Feature Alignment (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 13:30 | SDOD: Towards Reliable Object Detection under Diverse Rainy Conditions with Deraining and Mutual Learning (abstract) |
| 13:45 | YOLO-Pest A Model Design for Crop Pest Detection (abstract) |
| 14:00 | DOMVS:Unsupervised Multi-View Stereo for Dealing With Occlusion Scenes (abstract) |
| 14:15 | GartransNet: 3D garments animation via transmission optimized networks (abstract) |
| 14:30 | IMFDM: Improved Mamba-based Feature Decomposition Model for Multi-Modality Image Fusion (abstract) |
| 14:45 | Task-adaptive Channel Attention Graph Network for Few-shot 3D Point Cloud Classification (abstract) |
Zoom Link: https://us06web.zoom.us/j/82346226482?pwd=Rwc3dmFUMa4UZ7qcAcfcsBPjJ7baXv.1 Meeting ID: 823 4622 6482 Passcode: CGI2025
| 13:30 | DL-DETR: Exploring the Future Directions of Fusion Between Dictionary Learning and DETR (abstract) |
| 13:45 | Facial Action Unit Detection with Iterative Rank Reduction Adapter and Directional Attention (abstract) |
| 14:00 | Intrinsic Reflective Symmetry Axis Curve Generation for Meshes (abstract) |
| 14:15 | SCAU-Net: An Efficient Module for Multi-scale Feature Extraction and Aggregation in Video Super-Resolution (abstract) |
| 14:30 | A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images (abstract) |
| 14:45 | CoFormer:Coupling Attentive Model for Visual Sentiment Analysis with Hierarchical Emotion Loss (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 15:40 | Multilevel Monte Carlo for Asymptotically Efficient Path Tracing (abstract) |
| 15:55 | Video Sketching using Multi-domain Guidance and Implicit Encoding (abstract) |
| 16:10 | Scene-Enhanced Social Interpretable Movement Behavior for Multimodal Pedestrian Trajectory Prediction (abstract) |
| 16:25 | ConDT: A 2D curve reconstruction algorithm based on a constrained-neighbor proximity graph (abstract) |
| 16:40 | MindCanvas: A Human-Centric Approach to AI-Driven Artistic Creation Through Brain Signals (abstract) |
| 16:55 | Graph Convolutional Networks for 3D Skeleton-Based Scoliosis Screening Using Gait Sequences (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 15:40 | GUM-DiT: A Foundation Model for Generating Urban Morphological Layouts (abstract) |
| 15:55 | WA-FDNet: A Unified Weight Adaptation Network for Multimodal Image Fusion and Object Detection (abstract) |
| 16:10 | Sequential Fluid Image Generation Network Based on Spatio-Temporal Swin Transformer (abstract) |
| 16:25 | Learning Human-Object Interactions in Videos with Optical Flow (abstract) |
| 16:40 | TADT: Task-aligned Deep Tracking (abstract) |
| 16:55 | Reproducing the Appearance of Metallic Materials by Capturing Long-Range Dependencies using Image-to-Image Translation Network with Vision Transformer (abstract) |
Zoom Link: https://us06web.zoom.us/j/82346226482?pwd=Rwc3dmFUMa4UZ7qcAcfcsBPjJ7baXv.1 Meeting ID: 823 4622 6482 Passcode: CGI2025
| 15:40 | Veiled Diffusion: A Diffusion-Based Anti-Customization Adversarial Attack Method via Semantic Misalignment and Low-Frequency Information (abstract) |
| 15:55 | Generating Multi-Illumination Leaf Images through Single-Image Material Estimation for Robust Disease Recognition (abstract) |
| 16:10 | Te3DFR: Texture-enabled 3D Face Reconstruction from Monocular Image via Self-supervised Learning (abstract) |
| 16:25 | Lightweight Image Super-Resolution Using Fine-Grained Feature Distillation in a Dense Residual U-Net (abstract) |
| 16:40 | Extending Implicit Density Projection for Multiphase Fluids (abstract) |
| 16:55 | CartoonAnimalPose: A New Dataset and Method for Cartoon Animal Pose Estimation (abstract) |
View this program: with abstractssession overviewtalk overview
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 10:25 | Few-shot Medical Image Segmentation via Query Transformation Learning (abstract) |
| 10:40 | Boosting Remote Semantic Segmentation Using Vision-and- language Foundation Model (abstract) |
| 10:55 | RaEUNet: A Retentive and Efficient UNet for Medical Image Segmentation (abstract) |
| 11:10 | Generating 3D fish motion skeleton via iterative optimization method and FishSkeletonNet (abstract) |
| 11:25 | Semantic-Orthogonal Multi-modal Attention Network for RGB-D Salient Object Detection (abstract) |
| 11:40 | Unified Cross-Domain Refinement Network for Camouflaged Object Detection (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 10:25 | StyleRegLoRA: An Improved Framework for SDXL LoRA Fine-tuning Towards Art Category Generation (abstract) |
| 10:40 | Latent Interpretation for Multi-View Face Synthesis across GAN and Diffusion via Conditional Reconstruction (abstract) |
| 10:55 | PeelMesh: Efficient Interactive Segmentation via Geodesic-Driven Dynamic Topological Updates (abstract) |
| 11:10 | ENViT-FAS: ENViT with Attack-Oriented Augmentation for Domain-Generalized Face Anti-Spoofing (abstract) |
| 11:25 | Machine Learning Approach for Color Selection near Light/Dark Boundaries Considering Emotional Impressions (abstract) |
| 11:40 | EX-YOLO: Improve YOLOv11 to achieve efficient detection of small targets of drones (abstract) |
Zoom Link: https://us06web.zoom.us/j/82346226482?pwd=Rwc3dmFUMa4UZ7qcAcfcsBPjJ7baXv.1 Meeting ID: 823 4622 6482 Passcode: CGI2025
| 10:25 | A Novel Approach to Defocus Region Detection in Phase-Shifting Structured Light 3D Reconstruction (abstract) |
| 10:40 | MatLayerNet: A Multi-Agent-Based Method for Text-to-PBR Material Generation (abstract) |
| 10:55 | Embedding Space Decomposition Meets Invertible Networks: A New Paradigm for Unpaired Low-Light Enhancement (abstract) |
| 11:10 | Robust bi-level optimization for monocular human and scene reconstruction (abstract) |
| 11:25 | A Privacy-preserving Collaborative 3D Design Framework for Copyright Protection (abstract) |
| 11:40 | Enhancing Vision Transformer for Fine-Grained Classification with Selective Attention Aggregation and Multi-Head Noise Suppression (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 13:30 | L2H-NeRF: Low- to High-Frequency-Guided NeRF for 3D Reconstruction With a Few Input Scenes (abstract) |
| 13:45 | Advancements and Challenges of Deep Learning in Virtual Try-On: A Comprehensive Review (abstract) |
| 14:00 | FaceCapGes: Real-Time Frame-by-Frame Gesture Generation from Audio, Facial Capture, and Head Pose (abstract) |
| 14:15 | Alphanumeric Fingerspelling: A New Large-Scale Dataset and Comparative Analysis of Methods for Indian Sign Language (abstract) |
| 14:30 | PLNet: Entropy-Guided Pseudo Label Refinement with Sensitivity-Specificity Enhancement for Medical Image Segmentation (abstract) |
| 14:45 | Texture and Geometry Optimization for 3D Reconstruction (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 13:30 | Enhancing Small Object Detection in Aerial Images Under Multi-Weather Conditions Using Modified YOLO (abstract) |
| 13:45 | BadHPE: Backdoor Attack for Precise Manipulation of Human Pose Estimation Models (abstract) |
| 14:00 | Fuzzy Logic-Based Virtual Leading Path Planning for Autonomous Underwater Vehicles: An Evaluation Index Approach (abstract) |
| 14:15 | Weakly Supervised Video Anomaly Detection via Temporal Dynamic Modeling and Semantic-Assisted Approach (abstract) |
| 14:30 | DAN: Dual-Attention Network for Occlusion-Robust 3D Hand Pose Estimation (abstract) |
| 14:45 | Coordinate-Aware Implicit Image Function for Arbitrary-Scale Image Super-Resolution (abstract) |
Zoom Link: https://us06web.zoom.us/j/82346226482?pwd=Rwc3dmFUMa4UZ7qcAcfcsBPjJ7baXv.1 Meeting ID: 823 4622 6482 Passcode: CGI2025
| 13:30 | Real-Time EEG-Based Fear Intensity Estimation for Virtual Reality Exposure Therapy (abstract) |
| 13:45 | Feature Replacement in Gaussian Splatting for 3D Stylization (abstract) |
| 14:00 | RelieFormer:End-to-End Bas Relief Generation via Transformer (abstract) |
| 14:15 | Multi-Granularity Feature Extraction Based on Long-Short Chains for Motion Retargeting (abstract) |
| 14:30 | D^2-Diff: Controllable Fashion Image Generation with Disentangled Style and Content (abstract) |
| 14:45 | MELD: A Multi-Element Latent Diffusion Model for Urban Greenspace Layout Generation (abstract) |
Zoom Link: https://polyu.zoom.us/j/89298697634?pwd=lWl32BN6kaRycVtGjmi3RW9BqhtiEj.1 Meeting ID: 892 9869 7634 Passcode: CGI2025
| 15:40 | BIDP: Brain-Inspired Dual-Process CNN-Transformer for Salient Object Detection (abstract) |
Zoom Link: https://us06web.zoom.us/j/81900726710?pwd=aEYm8qBzCJspHAYNhC3tBNbZvaoPBk.1 Meeting ID: 819 0072 6710 Passcode: CGI2025
| 15:40 | SigNet-TAM: Indian Sign Language Recognition with ResNet50-BiLSTM and Temporal Attention Mechanism (abstract) |