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

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.

.- YOLOv8_ODY:An Object Detection Model for Traffic SignsT.

.- Mask-Based Matching Enhancement for Unsupervised Point Cloud Registration.

.- Driver action recognition based on Dynamic Adaptive Transformer.

.- SimNET: A Deep learning macroscopic traffic simulation model for signal controlled urban road network.

.- UAV-LMDN: Lightweight Multi-Scale Small Object Detection Network for Unmanned Aerial Vehicle Perspective.

.- LRDN: Lightweight Risk Detection Network for Power System Operations.

.- Personalized Federated Learning by Model Pruning via Batch Normalization Layers.

.- IT-HMDM: Invertible Transformer for Human Motion Diffusion Model.

.- Fashion Image Retrieval Based on Multimodal Features Enhancement and Fusion.

.- Syntactic Enhanced Multi-Channel Graph Convolutional Network for Aspect-based Sentiment Analysis.

.- Intelligent Helmet System for Hazardous Area Detection based on Digital Twin Technology.

.- An Evaluation of a Simulation System for Visitors in Exhibit Halls.

.- Foley Agent: Automatic Sound Design and Mixing Agent for Silent Videos Driven by LLMs.

.- Deep Metric Learning with  Feature Aggregation for Generalizable Person Re-Identification.

.- Diverse 3D Human Pose Generation in Scenes based on Decoupled Structure.

.- A Combination Simulation Method for Low Orbit Large Scale Satellites via STK and NS2.

.- Semantic-Guided Prompt Learning Network for Generalized Zero-Shot Learning.

.- MiT-Unet: Mixed Transformer Unet for Transmission Line Segmentation in UAV Images.

.- Semantic-driven multi-character multi-motion 3D animation generation.

.- MSAR: A Mask Branch Module Integrating Multi-scale Attention And RefineNet.

.- Multi-level Knowledge Distillation for Class  Incremental Learning.

.- Research on the algorithm of helmet-wearing detection based on the optimized Mobilevit and Centernet.

.- Better Sampling, towards Better End-to-end small Object Detection.

.- Stealthily Launch Backdoor Attacks Against Deep Neural Network Models via Steganography.

.- Seat belt wearing detection based on Efficient Det_Ad.

.- DHNet: A Depth wise Separable Convolution-based High-Resolution Full Projector Compensation Network.

.- Denoising Implicit Feedback for Extractive Question Answering.

.- Iterative Consistent Attentional Diffusion Model for Multi-Contrast MRISuper-Resolution.