Computer Vision and Pattern Recognition: Attention-based Global-Local Graph Learning for Dynamic Facial Expression Recognition.- Implicit Representation for Interacting Hands Reconstruction from Monocular Color Images.- HQFS: High-quality Feature Selection for Accurate Change Detection.- FAFormer: Foggy Scene Semantic Segmentation by Fog-invariant Auxiliary Domain adaptation.- Video-based Person Re-identification With Long Short-Term Representation Learning.- Multi-semantic fusion model for generalized zero-shot skeleton-based action recognition.- Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation.- SECT: Sentiment-Enriched Continual Training for Image Sentiment Analysis.- Learn to Enhance the Negative Information in Convolutional Neural Network.- Task-Agnostic Generalized Meta-Learning based on MAML for Few-shot Bearing Fault Diagnosis.- Weakly Supervised Image Matting via Patch Clustering.- Attention-guided Motion Estimation for Video Compression.- Cloud Detection from Remote Sensing Images by Cascaded U-shape Attention Networks.- Ar3dHands: A Dataset and Baseline for Real-time 3D Hand Pose Estimation from Binocular Distorted Images.- TANet: Adversarial Network via Tokens Transformer for Universal Domain Adaptation.- GLM: A Model Based on Global-Local Joint Learning for Emotion Recognition from Gaits using Dual-Stream Network.- HuMoMM: A Multi-Modal Dataset and Benchmark for Human Motion Analysis.- Enhanced Frequency Information for Image Dehazing.- Energy-Efficient Robotic Arm Control Based on Differentiable Spiking Neural Networks.- Uncover the Body: Occluded Person Re-identification via Masked Image Modeling.- Enhancing Adversarial Transferability From the Perspective of Input Loss Landscape.- Local-Fusion Diffusion Model for Enhancing Few-Shot Image Generation.- Table Structure Recognition of Historical Dongba Documents.- LE2Fusion: A novel local edge enhancement module for infrared and visible image fusion.- Complex Glyph Enhancement for License Plate Generation.- High Fidelity Virtual Try-On via Dual Branch Bottleneck Transformer.- A Road Damage Segmentation Method for Complex  Environment Based on Improved UNet.- Structural Reparameterization Network on Point Cloud Semantic Segmentation.- Physical Key Point Detection Algorithm based on Multi-Scale Feature Fusion.- Skeleton Based Dynamic Hand Gesture Recognition using Short Term Sampling Neural Networks (STSNN).- Face Anti-spoofing Based on Client Identity Information and Depth Map.- Attention-based RGBD Fusenet for Monocular 3D Body Geometry and Pose Reconstruction.- Distortion-Aware Mutual Constraint for Screen Content Image Quality Assessment.- Visual Realism Assessment for Face-swap Videos.- 360° Omnidirectional Salient Object Detection with Multi-scale Interaction and Densely-connected Prediction.