DeepAI AI Chat
Log In Sign Up

Deep Association Learning for Unsupervised Video Person Re-identification

by   Yanbei Chen, et al.

Deep learning methods have started to dominate the research progress of video-based person re-identification (re-id). However, existing methods mostly consider supervised learning, which requires exhaustive manual efforts for labelling cross-view pairwise data. Therefore, they severely lack scalability and practicality in real-world video surveillance applications. In this work, to address the video person re-id task, we formulate a novel Deep Association Learning (DAL) scheme, the first end-to-end deep learning method using none of the identity labels in model initialisation and training. DAL learns a deep re-id matching model by jointly optimising two margin-based association losses in an end-to-end manner, which effectively constrains the association of each frame to the best-matched intra-camera representation and cross-camera representation. Existing standard CNNs can be readily employed within our DAL scheme. Experiment results demonstrate that our proposed DAL significantly outperforms current state-of-the-art unsupervised video person re-id methods on three benchmarks: PRID 2011, iLIDS-VID and MARS.


page 2

page 8


Unsupervised Tracklet Person Re-Identification

Most existing person re-identification (re-id) methods rely on supervise...

Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization

Existing methods for person re-identification (Re-ID) are mostly based o...

Unsupervised Person Re-identification by Deep Learning Tracklet Association

Mostexistingpersonre-identification(re-id)methods relyon supervised mode...

Towards Precise Intra-camera Supervised Person Re-identification

Intra-camera supervision (ICS) for person re-identification (Re-ID) assu...

CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

This paper proposes a self-supervised learning method for the person re-...

Generalizable Re-Identification from Videos with Cycle Association

In this paper, we are interested in learning a generalizable person re-i...

Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data

The ability of a researcher to re-identify (re-ID) an individual animal ...