activity
20182026
most citedReal-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification

404 citations · 484 across the 13 of their papers we have counts for

collaborators
Showing 2020Show all

5 papers · 1 filter

cs.CV2020★ 5 cited

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification

Tianyu Zhang, Lingxi Xie, Longhui Wei +4

The main difficulty of person re-identification (ReID) lies in collecting annotated data and transferring the model across different domains. This paper presents UnrealPerson, a no…

math.PR2020

On the percolative properties of the intersection of two independent interlacements

Zijie Zhuang

We prove the existence of non-trivial phase transitions for the intersection of two independent random interlacements and the complement of the intersection. Some asymptotic result…

cs.CV2020★ 2 cited

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

Haitian Zeng, Haizhou Ai, Zijie Zhuang +1

Learning to predict multiple attributes of a pedestrian is a multi-task learning problem. To share feature representation between two individual task networks, conventional methods…

cs.CV2020★ 12 cited

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

Long Chen, Haizhou Ai, Rui Chen +2

Estimating 3D poses of multiple humans in real-time is a classic but still challenging task in computer vision. Its major difficulty lies in the ambiguity in cross-view association…

cs.CV2020★ 6 cited

Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization

Zijie Zhuang, Longhui Wei, Lingxi Xie +5

The fundamental difficulty in person re-identification (ReID) lies in learning the correspondence among individual cameras. It strongly demands costly inter-camera annotations, yet…