CVPR2020/2021行人检测重识别等论文,共33篇

2020

行人检测

1. Detection in Crowded Scenes: One Proposal, Multiple Predictions
2. NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing
3. STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction
4. .Where, What, Whether: Multi-Modal Learning Meets Pedestrian Detection
5. Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians
6. Attention Scaling for Crowd Counting
7. Reverse Perspective Network for Perspective-Aware Object Counting
8. Adaptive Dilated Network With Self-Correction Supervision for Counting
9. Camera On-Boarding for Person Re-Identification Using Hypothesis Transfer Learning
10. Hierarchical Clustering With Hard-Batch Triplet Loss for Person Re-Identification
11. Real-World Person Re-Identification via Degradation Invariance Learning
12. Unity Style Transfer for Person Re-Identification
13. Online Joint Multi-Metric Adaptation From Frequent Sharing-Subset Mining for Person Re-Identification
14. Style Normalization and Restitution for Generalizable Person Re-Identification
15. Relation-Aware Global Attention for Person Re-Identification
16. Salience-Guided Cascaded Suppression Network for Person Re-Identification

 基于视频的人员重识别

1. Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification
2. Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
3. Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-Based Person Re-Identification

对抗攻击+人员重识别

1. Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking

 跨分辨率人员重识别

1. Inter-Task Association Critic for Cross-Resolution Person Re-Identification

 非监督人员重识别

1. Unsupervised Person Re-Identification via Softened Similarity Learning
2. Unsupervised Person Re-Identification via Multi-Label Classification

 遮挡人员重识别

1. High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
2. Pose-Guided Visible Part Matching for Occluded Person ReID

 跨域人员重识别

1. AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification
2. Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain Person Re-Identification
3. Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
4. .Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer

基于射频信号的人员重识别

1. Learning Longterm Representations for Person Re-Identification Using Radio Signals

着装改变人员重识别数据集

1. COCAS: A Large-Scale Clothes Changing Person Dataset for Re-Identification

步态识别

1. GaitPart: Temporal Part-Based Model for Gait Recognition
2. Gait Recognition via Semi-supervised Disentangled Representation Learning to Identity and Covariate Features

2021

拥挤人群计数

• Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
• Cross-View Cross-Scene Multi-View Crowd Counting
• A Generalized Loss Function for Crowd Counting and Localization
  行人检测 
• Variational Pedestrian Detection
• Generalizable Pedestrian Detection: The Elephant In The Room
  行人跟踪
• Tracking Pedestrian Heads in Dense Crowd
  步态识别
•  Cross-View Gait Recognition with Deep Universal Linear Embeddings