Pattern Recognition and Computer Vision 4th Chinese Conference, PRCV 2021, Beijing, China, October 29 – November 1, 2021, Proceedings, Part I

The 4-volume set LNCS 13019, 13020, 13021 and 13022 constitutes the refereed proceedings of the 4th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2021, held in Beijing, China, in October-November 2021.

The 201 full papers presented were carefully reviewed and selected from 513 submissions. The papers have been organized in the following topical sections: Object Detection, Tracking and Recognition; Computer Vision, Theories and Applications, Multimedia Processing and Analysis; Low-level Vision and Image Processing; Biomedical Image Processing and Analysis; Machine Learning, Neural Network and Deep Learning, and New Advances in Visual Perception and Understanding.

Object Detection, Tracking and Recognition.- High-performance Discriminative Tracking with Target-aware Feature Embeddings.-3D Multi-Object Detection and Tracking with Sparse Stationary LiDAR.- CRNet: Centroid Radiation Network for Temporal Action Localization.- Weakly Supervised Temporal Action Localization with Segment-Level Labels.- Locality-constrained collaborative representation with multi-resolution dictionary for face recognition.- Fast and Fusion: Real-time Pedestrian Detector Boosted by Body-head Fusion.- STA-GCN: Spatio-Temporal AU Graph Convolution Network for Facial Micro-Expression Recognition.- Attentive Contrast Learning Network for Fine-grained Classification.- Relation-Based Knowledge Distillation for Anomaly Detection.- High Power-efficient and Performance-density FPGA Accelerator for CNN-based Object Detection.- Relation-Guided Actor Attention for Group Activity Recognition.- MVAD-Net: Learning View-Aware and Domain-Invariant Representation for Baggage Re-Identification.- Joint Attention Mechanism for Unsupervised Video Object Segmentation.-Foreground Feature Selection and Alignment for Adaptive Object Detection.- Exploring Category-shared and Category-specific Features for Fine-Grained Image Classification.-Deep Mixture of Adversarial Autoencoders Clustering Network.- SA-InterNet: Scale-aware Interaction Network for Joint Crowd Counting and Localization.- Conditioners for Adaptive Regression Tracking.- Attention Template Update Model for Siamese Tracker.- Insight on Attention Modules for Skeleton-Based Action Recognition.- AO-AutoTrack: Anti-Occlusion Real-Time UAV Tracking Based on Spatio-temporal Context.- Two-stage Recognition Algorithm for Untrimmed  Converter Steelmaking Flame Video.- Scale-aware Multi-branch Decoder for Salient Object Detection.- Dense End Face Detection Network for Counting Bundled Steel Bars Based on Densely End Face Detection Network for Counting Bundled Steel Bars Based on YoloV5.- POT: A Dataset of Panoramic Object Tracking.- DP-YOLOv5:Computer Vision-Based Risk Behavior Detection in Power Grids.-Distillation-based Multi-Exit Fully Convolutional Network for Visual Tracking.-Handwriting Trajectory Reconstruction using Spatial-Temporal Encoder-Decoder Network.- Scene Semantic Guidance for Object Detection.- Training Person Re-Identification Networks with Transferred Images.- ACFIM: Adaptively Cyclic Feature Information- interaction model for Object Detection.- Research of robust video object tracking algorithm based on Jetson Nano embedded platform.- Classification-IoU Joint Label Assignment For End-to-End Object Detection.- Joint Learning Appearance and Motion Models for Visual Tracking.- ReFlowNet: Revisiting Coarse-to-fine Learning of Optical Flow.- Local Mutual Metric Network for Few-Shot Image Classification.- SimplePose V2: Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation.- Control Variates for Similarity Search.- Pyramid Self-Attention for Semantic Segmentation.-Re-identify Deformable Targets for Visual Tracking.- End-to-End Detection and Recognition of Arithmetic Expressions.- FD-Net: A Fully Dilated Convolutional Network for Historical Document Image Binarization.- Appearance-Motion Fusion Network for Video Anomaly Detection.- Can DNN Detectors Compete against Human Vision in Object Detection Task?.- Group Re-Identification Based on single feature attention learning network(SFALN).- Contrastive Cycle Consistency Learning for Unsupervised Visual Tracking.- Group-Aware Disentangle Learning for Head Pose Estimation.- Facilitating 3D Object Tracking in Point Clouds with Image Semantics and Geometry.- Multi-Criteria Confidence Evaluation for Robust Visual Tracking.