Picture for Zijie Zhuang

Zijie Zhuang

Spatiotemporal Transformer for Video-based Person Re-identification

Add code
Mar 30, 2021
Figure 1 for Spatiotemporal Transformer for Video-based Person Re-identification
Figure 2 for Spatiotemporal Transformer for Video-based Person Re-identification
Figure 3 for Spatiotemporal Transformer for Video-based Person Re-identification
Figure 4 for Spatiotemporal Transformer for Video-based Person Re-identification
Viaarxiv icon

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification

Add code
Dec 09, 2020
Figure 1 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
Figure 2 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
Figure 3 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
Figure 4 for UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
Viaarxiv icon

Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognition

Add code
Apr 07, 2020
Figure 1 for Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognition
Figure 2 for Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognition
Figure 3 for Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognition
Figure 4 for Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognition
Viaarxiv icon

Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS

Add code
Mar 09, 2020
Figure 1 for Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
Figure 2 for Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
Figure 3 for Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
Figure 4 for Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
Viaarxiv icon

Disassembling the Dataset: A Camera Alignment Mechanism for Multiple Tasks in Person Re-identification

Add code
Jan 23, 2020
Figure 1 for Disassembling the Dataset: A Camera Alignment Mechanism for Multiple Tasks in Person Re-identification
Figure 2 for Disassembling the Dataset: A Camera Alignment Mechanism for Multiple Tasks in Person Re-identification
Figure 3 for Disassembling the Dataset: A Camera Alignment Mechanism for Multiple Tasks in Person Re-identification
Figure 4 for Disassembling the Dataset: A Camera Alignment Mechanism for Multiple Tasks in Person Re-identification
Viaarxiv icon

Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation

Add code
Sep 20, 2019
Figure 1 for Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation
Figure 2 for Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation
Figure 3 for Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation
Viaarxiv icon

Cross-Resolution Person Re-identification with Deep Antithetical Learning

Add code
Oct 24, 2018
Figure 1 for Cross-Resolution Person Re-identification with Deep Antithetical Learning
Figure 2 for Cross-Resolution Person Re-identification with Deep Antithetical Learning
Figure 3 for Cross-Resolution Person Re-identification with Deep Antithetical Learning
Figure 4 for Cross-Resolution Person Re-identification with Deep Antithetical Learning
Viaarxiv icon

Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification

Add code
Sep 12, 2018
Figure 1 for Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification
Figure 2 for Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification
Figure 3 for Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification
Figure 4 for Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification
Viaarxiv icon