3D Computer Vision and Reconstruction, Robots and Autonomous Driving.- Locally Geometry-Aware Improvements of LOP for Ecient Skeleton Extraction.- Spherical Transformer: Adapting Spherical Signal to Convolutional Networks.- Waterfall-Net: Waterfall Feature Aggregation for Point Cloud Semantic Segmentation.- Sparse LiDAR and Binocular Stereo Fusion Network for 3D Object Detection.- Full Head Performance Capture Using Multi-Scale Mesh Propagation.- Learning Cross-domain Features for Domain Generalization on Point Clouds.- Unsupervised Pre-training for 3D Object Detection with Transformer.- Global Patch Cross-Attention for Point Cloud Analysis.- EEP-Net: Enhancing local neighborhood features and Ecient semantic segmentation of scale Point Clouds.- CARR-Net: Leveraging on Subtle Variance of Neighbors for Point Cloud Semantic Segmentation.- 3D Meteorological Radar Data Visualization with Point Cloud Completion and Poisson Surface Reconstruction.- JVLDLoc: a Joint Optimization of Visual-LiDAR Constraints and Direction Priors for Localization in Driving Scenario.- A Single-pathway Biomimetic Model for Potential Collision Prediction.- PilotAttnNet: Multi-Modal Attention Network for End-to-End Steering
Control.- Stochastic Navigation Command Matching for Imitation Learning of a Driving Policy.- Recognition, Remote Sensing.- Group Activity Representation Learning with Self-Supervised Predictive Coding.- Skeleton-Based Action Quality Assessment via Partially Connected LSTM with Triplet Losses.- Hierarchical Long-Short Transformer for Group Activity Recognition.- GNN-based structural dynamics simulation for modular buildings.- Semantic-Augmented Local Decision Aggregation Network for Action Recognition.- Consensus-Guided Keyword Targeting for Video Captioning.- Handwritten Mathematical Expression Recognition via GCAttention- Based Encoder and Bidirectional Mutual Learning Transformer.- Semi- and Self-Supervised Learning for Scene Text Recognition with Fewer Labels.- TMCR: A Twin Matching Networks for Chinese Scene Text Retrieval.- Thai Scene Text Recognition with Character Combination.- Automatic Examination Paper Scores Calculation and Grades Analysis Based on OpenCV.- Efficient License Plate Recognition via Parallel Position-aware Attention.- Semantic-Aware Non-Local Network for Handwritten Mathematical Expression Recognition.- Math Word Problem Generation with Memory Retrieval.- Traditional Mongolian Script Standard Compliance Testing Based on Deep Residual Network and Spatial Pyramid Pooling.- FOV Recognizer: Telling the Field of View of Movie Shots.- Multi-Level Temporal Relation Graph for Continuous Sign Language Recognition.-Beyond Vision: A Semantic Reasoning Enhanced Model for Gesture Recognition with Improved Spatiotemporal Capacity.- SemanticGAN: Facial Image Editing with Semantic to Realize Consistency.- Least-squares Estimation of Keypoint Coordinate for Human Pose Estimation.- Joint Pixel-level and Feature-level Unsupervised Domain Adaptation for Surveillance Face Recognition.- Category-oriented Adversarial Data Augmentation via Statistic Similarity for Satellite Images.- A Multi-scale Convolutional Neural Network Based on Multilevel Wavelet Decomposition for Hyperspectral Image Classification.- High Spatial Resolution Remote Sensing Imagery Classification Based on Markov Random Field Model Integrating Granularity and Semantic Feature.- Feature Difference Enhancement Fusion for Remote Sensing Image Change Detection.- WAFormer Ship Detection in SAR Images Based on Window-aware Swin-Transformer.- EllipseIoU: A General Metric for Aerial Object Detection.- Transmission tower detection algorithm based on feature-enhanced convolutional network in remote sensing image.- Vision Analysis and Understanding.- Mining Diverse Clues with Transformers for Person Re-identification.- Mutual Learning Inspired Prediction Network for Video Anomaly Detection.- Weakly Supervised Video Anomaly Detection with Temporal and Abnormal Information.- Towards Class Interpretable Vision Transformer with Multi-Class-Tokens.- Multimodal Violent Video Recognition based on Mutual Distillation.- YFormer: a New Transformer Architecture for Video-query Based Video Moment Retrieval.- Hightlight Video Detection in Figure Skating.- Memory Enhanced Spatial-Temporal Graph Convolutional Autoencoder for Human-related Video Anomaly Detection.- Background Suppressed and Motion Enhanced Network for Weakly Supervised Video Anomaly Detection.- Dirt Detection and Segmentation Network for Autonomous Washing Robots.- Finding Beautiful and Happy Images for Mental Health and Well-being Applications.- Query-UAP: Query-ecient Universal Adversarial Perturbation for Large-scale Person Re-Identification Attack.- Robust Person Re-identification with Adversarial Examples Detection and Perturbation Extraction.- Self-Supervised and Template-Enhanced Unknown-Defect Detection.- JoinTW: A Joint Image-to-Image Translation and Watermarking Method.
