Program for Thursday, July 17th: Talk View

PROGRAM FOR THURSDAY, JULY 17TH: TALK VIEW

Days:

previous day

next day

all days

View: with abstracts session overview

8:30

9:00

9:30

10:00

10:30

11:00

11:30

12:00

12:30

13:00

13:30

14:00

14:30

15:00

15:30

16:00

16:30

17:00

08:30-17:00 CGI 2025 Registration

09:00-09:15 Welcome to CGI 2025

09:15-10:15

3D Reconstructions from Unoriented Points: Recent Advances and Emerging Trends

Ying He

10:15-10:40 Tea Break

10:40-10:55

A Two Stage Controllable Co-Speech Gesture Generation Method

Zeyu Peng, Dan Ma, Xiangwei Lv

10:55-11:10

Multi-Agent Learning with Hierarchical Prompt for Efficient 3D Human Pose Estimation in Virtual

Xingquan Cai, Kaijie Qu, Luyao Wang, Shanshan He, Yan Hu

11:10-11:25

Turbulence Estimation in Smoke Simulation via Curvature-Based Image Features

Syuhei Sato, Ryosuke Kawazumi, Yoshinori Dobashi

11:25-11:40

Prototype XR Elastodynamics System for Disaster Medical Response

Wang, Aoki, Murakami, Shimoe, Senoo, Date, Shichinohe, Abe, Kanai, Konno

11:40-11:55

Person-In-Situ: Scene-Consistent Human Image Insertion with Occlusion-Aware Pose Control

Shun Masuda, Yuki Endo, Yoshihiro Kanamori

10:40-10:55

StencilQR: Connectivity-enhanced Fabricable QR Codes for Stencil

Naoki Kita

10:55-11:10

Recognize Me If You Can: Two-stream Adversarial Transfer for Facial Privacy Protection using Fine-grained

Ruiling Li, Ming Gao, Xiaogang Jin

11:10-11:25

Transforming Time and Space: Efficient Video Super-Resolution with Hybrid Attention and Deformable

Linling Jiang, Fan Zhang, Caiming Zhang

11:25-11:40

Exploring Structural Lines for Interior Floorplan Segmentation

Bingchen Yang, Haiyong Jiang, Zhengda Lu, Jun Xiao

11:40-11:55

OSH-Splat: Optimizable Semantic Hyperplanes for Enhanced 3D Language Feature Gaussian Splatting

Ruijie Xu, Yuzhou Ji, Xin Tan, Lizhuang Ma

10:40-10:55

BWANet: A low-light image detail enhancement network with multi-scale large receptive fields

Haiyuan Tang

10:55-11:10

Guiding Steady Fluid Flow with Terrain-Based Repulsive Forces

Yuki Kimura, Syuhei Sato, Masataka Sawayama, Yoshinori Dobashi

11:10-11:25

Knowledge Graph Completion by Integrating Local and Global Features

Guoxi Zeng, Lanfeng Zhou

11:25-11:40

TerraFusion: Joint Generation of Terrain Shape and Texture Using Latent Diffusion Models

Kazuki Higo, Toshiki Kanai, Yuki Endo, Yoshihiro Kanamori

11:40-11:55

Bimodal VIT Adaptive Cross-Fusion Micro-Expression Recognition Based on ECG-QRS Waves

Fan Zhang, Lin Chai

12:10-13:30 Lunch (Ju Yin House Seafood Restaurant)

13:30-13:45

PDFT: Parameter-Diminish Fine-Tuning for Transformer-based Models

M. Zhang, W. Meng, M. Jia, J. Gu, Y. Shao, C. Wang, R. Xu, Z. Ma, X. Zhang

13:45-14:00

Dual-Path Spatio-Temporal Mamba for Skeleton-Based Action Recognition

Jie Zhao, Feng Zhou, Ju Dai, Junjun Pan, Hongwen Xu

14:00-14:15

Boosting Memory Network for Video Object Segmentation in Complex Scenes

Yuhang Yi, Yan Gui, Zhuo Liu

14:15-14:30

ViT-BF: Vision Transformer with Border-aware Features for Visual Tracking

K. Yang, W. Zhang, P. Li, J. Liang, T. Peng, J. Chen, L. Li, X. Hu

14:30-14:45

Physics-Guided Deep Learning Framework with Attention for Image Denoising

Shengjun Liu, Ting Zhang, Ruoxi Deng, Xinru Liu, Hanchao Liu

14:45-15:00

Interpretable Two-Stage Action Quality Assessment via 3D Human Pose Estimation and Dynamic Feature

Shouming Hou, Aoyu Xia, Zixuan Lu, Weibo Yang

13:30-13:45

SDOD: Towards Reliable Object Detection under Diverse Rainy Conditions with Deraining and Mutual

Zhiyong Wei, Hongda Qin, Ningjiang Chen

13:45-14:00

YOLO-Pest A Model Design for Crop Pest Detection

Wei Wei, Jiabao Duan, Jian Yun, Xiaodong Duan

14:00-14:15

DOMVS:Unsupervised Multi-View Stereo for Dealing With Occlusion Scenes

Mingwei Cao, Qiuju Wang, Ning Li, Haifeng Zhao

14:15-14:30

GartransNet: 3D garments animation via transmission optimized networks

Tao Peng, Wenjie Yue, Zili Zhang, Zhe Chen, Junping Liu, Xinrong Hu, Li Li

14:30-14:45

IMFDM: Improved Mamba-based Feature Decomposition Model for Multi-Modality Image Fusion

Ziheng Ling, Hui Wang, Lina Chen, Hong Gao

14:45-15:00

Task-adaptive Channel Attention Graph Network for Few-shot 3D Point Cloud Classification

Ge Liu, Zhongqiang Zhang, Jingren Xie, Xiangzhong Fang

13:30-13:45

DL-DETR: Exploring the Future Directions of Fusion Between Dictionary Learning and DETR

Fuyuan Liu, Dezheng Ji, Hualai Si, Yuxuan Guo

13:45-14:00

Facial Action Unit Detection with Iterative Rank Reduction Adapter and Directional Attention

Zhiwen Shao, Chunyu Li, Fan Zhang, Hancheng Zhu, Rui Yao, Bing Liu

14:00-14:15

Intrinsic Reflective Symmetry Axis Curve Generation for Meshes

Batuhan Tosyalı, Yusuf Sahillioğlu

14:15-14:30

SCAU-Net: An Efficient Module for Multi-scale Feature Extraction and Aggregation in Video

Xiaonan He, Yukun Xia, Bangshu Xiong, Yuhang Ye

14:30-14:45

A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed

Y. Fang, Y. Cai, J. Aryal, Q. Zhu, H. Huang, C. Zhang, L. Fan

14:45-15:00

CoFormer:Coupling Attentive Model for Visual Sentiment Analysis with Hierarchical Emotion Loss

Gaifang Luo, Hao Zhang, Xiao Han, Zhaoyu Xiong, Dan Xu

15:10-15:40 Tea Break

15:40-15:55

Multilevel Monte Carlo for Asymptotically Efficient Path Tracing

Wonjun Lee

15:55-16:10

Video Sketching using Multi-domain Guidance and Implicit Encoding

Xiaonan Fang, Muhan Chang

16:10-16:25

Scene-Enhanced Social Interpretable Movement Behavior for Multimodal Pedestrian Trajectory

Teng Zhang, Bo Yang, Jianlin Zhu, Xincheng Hu

16:25-16:40

ConDT: A 2D curve reconstruction algorithm based on a constrained-neighbor proximity graph

Joms Antony, Minu Reghunath, Safeer Babu Thayyil, Ramanathan Muthuganapathy

16:40-16:55

MindCanvas: A Human-Centric Approach to AI-Driven Artistic Creation Through Brain Signals

Qian Wang, Liyan Wei, Maaike Kleinsmann, Yike Guo, Pan Wang

16:55-17:10

Graph Convolutional Networks for 3D Skeleton-Based Scoliosis Screening Using Gait Sequences

Zizhao Peng, Zihan Wang, Mengying Sun, Zheng Lv, Yan Wang, Ping Li, Fengwei An

15:40-15:55

GUM-DiT: A Foundation Model for Generating Urban Morphological Layouts

Xiaohang Dong, Qicheng Li, Hui Liang, Xu Zhang, Hualong Yu

15:55-16:10

WA-FDNet: A Unified Weight Adaptation Network for Multimodal Image Fusion and Object Detection

Yanyin Guo, Zhiyuan Zhang, Ying Luo, Junwei Li

16:10-16:25

Sequential Fluid Image Generation Network Based on Spatio-Temporal Swin Transformer

Zhiyu Ge, Changjun Zou

16:25-16:40

Learning Human-Object Interactions in Videos with Optical Flow

Qiyue Li, Pengchao Wang, Yingbin Wang, Yichuan Yin

16:40-16:55

TADT: Task-aligned Deep Tracking

Mengting Zhang, Zixin You, Qun Li, Kai Yang, Xinrong Hu

16:55-17:10

Reproducing the Appearance of Metallic Materials by Capturing Long-Range Dependencies using Image-to-Image Translation Network with Vision

Kaito Kojima, Taishi Iriyama, Takashi Komuro

15:40-15:55

Veiled Diffusion: A Diffusion-Based Anti-Customization Adversarial Attack Method via Semantic Misalignment and Low-Frequency

Lisha Li, Xiaolin Zhang, Jingyu Wang, Lixin Liu, Fengxi Sun

15:55-16:10

Generating Multi-Illumination Leaf Images through Single-Image Material Estimation for Robust Disease

Jiahui Chen, Yu Zhang, Xiaogang Wang

16:10-16:25

Te3DFR: Texture-enabled 3D Face Reconstruction from Monocular Image via Self-supervised Learning

Yishen Bi, Chen Wang, Lei Li, Yiran Shen, Yuanfeng Zhou

16:25-16:40

Lightweight Image Super-Resolution Using Fine-Grained Feature Distillation in a Dense Residual U-Net

Haoran Jia, Xin Wang, Tongtai Cao, Huaying Hao, Yue Liu

16:40-16:55

Extending Implicit Density Projection for Multiphase Fluids

Robert Dennison, Steve Maddock

16:55-17:10

CartoonAnimalPose: A New Dataset and Method for Cartoon Animal Pose Estimation

Longlong Jin, Shizhe Zhou