Computer Animation and Social Agents 37th International Conference, CASA 2024, Wuhan, China, June 5–7, 2024, Revised Selected Papers, Part II

This two-volume set, CCIS 2374 and CCIS 2375, constitutes the revised selected papers from the 37th International Conference on Computer Animation and Social Agents, CASA 2024, held in Wuhan, China, during June 5-7, 2024.

The 60 papers presented in these two volumes were carefully reviewed and selected from 208 submissions. These papers focus on various aspects of Computer Animation and Social Agents, such as Motion Capture & Retargeting, Physics-based Animation, Vision-based Techniques, Behavioral Animation, Facial Animation, Image-based Animation, Virtual Humans, Crowd Simulation, AI-based Animation, Deep Learning methods, Virtual humans and avatars, and 3D Physiological Humans.

.- Augmented Knowledge Distillation via Contrastive Learning.

.- Near-Eye Gaze Estimation in Virtual Reality Based on Deep Learning.

.- N-Sand Table A Multi-User Interactive Virtual Sand Table Based on NeRF Technology.

.- A weakly supervised crowd counting method  based on contrastive deep supervision.

.- The Detection and Rectification for Identity-Switch Based on the Unfalsified Control.

.- LDSBC: Lightweight Detection Network for Student Behavior in Classroom Scenario.

.- YOLO-DPW: An Efficient Real-time Fabric Defect Detection Model.

.- Quadrotor Unmanned Aerial Vehicle Trajectory Tracking Under Event-Triggered Sliding Mode Control.

.- Emotion Loss Attacking : Adversarial Attack Perception for Skeleton based on Multi-dimensional Features.

.- Method of Ionospheric Delay Positioning Error Correction Based on Transformer Model Prediction.

.- RFBR-IR:Regularized Frequency BRDF Reconstruction Inverse Rendering.

.- A lightweight camouflaged object detection model based on improved attention mechanism.

.- A Fabric Defect Detection Method Based on Improved YOLOv5.

.- UBAViz: User Behavior Analyzing in Literature Resources by Modeling User Behavior Sequences ..

.- ACDiff: Angle Craft Diffusion Model for Novel  View Synthesis.

.- A Training and Evaluation System for Magnetic-Actuated Virtual Vessel Interventional Surgery.

.- Self-Adapting NeRF: Non-ideal video based NeRF for high-quality novel view synthesis.

.- AnisoVector: Separable Anisotropic Set Abstraction and Group Vector Attention for Efficient Point Cloud Analysis.

.- Automatic code generation from GUI screenshots with vision-language models.

.- SymMoment: A Symbol Recognition System using Multiple Moments and Multicore Computing.

.- DBFF-PCGC: Dual-Branch Feature Fusion for Point Cloud Geometry Compressio.

.- Camouflaged Object Detection Based On Edge-Feature Interationt.

.- EyeGlove: Enhancing Smart Glove with Visual Information to Assist Students in Conducting Chemistry Experiments in Mixed Reality Laboratory.

.- Multilevel Topology Structure-aware Network for 3D Hand Pose Estimation.

.- Research on Garment Image Retrieval Method Based on Transformer and Multi-layer Feature Fusion.

.- Hybrid Attention Mechanism for 3D LIDAR Point Clouds Semantic Segmentation.

.- Think Twice Before Acting: Efficient Knowledge Distillation for 6-DOF Camera Relocalization.

.- A Spatially Enhanced CNN and Multiscale Transformer Fusion Approach for Chest Radiograph Registration.

.- The Phantom Dance: Personalized Anatomical Skeleton Inference from Monocular Views.

.- Research on Human-Robot Collaboration Safety Model and Key Algorithms in Assembly Systems.

.- Seam Carving Empowered by Reinforcement Learning for Optimal Content Preservation.

.- Robust Mesh Denoising Based on Weighted Least Squares.