paper-with-me

Papers

Unsupervised Video Person Re-identification via Noise and Hard frame Aware Clustering

2021-06-10 · Pengyu Xie, Xin Xu, Zheng Wang, Toshihiko Yamasaki

Unsupervised video-based person re-identification (re-ID) methods extract richer features from video tracklets than image-based ones. The state-of-the-art methods utilize clustering to obtain pseudo-labels and train the models iteratively. However, they underestimate the influence of two kinds of frames in the tracklet: 1) noise frames caused by detection errors or heavy occlusions exist in the tracklet, which may be allocated with unreliable labels during clustering; 2) the tracklet also contains hard frames caused by pose changes or partial occlusions, which are difficult to distinguish but informative. This paper proposes a Noise and Hard frame Aware Clustering (NHAC) method. NHAC consists of a graph trimming module and a node re-sampling module. The graph trimming module obtains stable graphs by removing noise frame nodes to improve the clustering accuracy. The node re-sampling module enhances the training of hard frame nodes to learn rich tracklet information. Experiments conducted on two video-based datasets demonstrate the effectiveness of the proposed NHAC under the unsupervised re-ID setting.

📄 PDF Abstract BibTeX arXiv:2106.05441

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringPerson Re-IdentificationVideo-Based Person Re-Identification

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

Unleashing the Potential of Tracklets for Unsupervised Video Person Re-Identification

2024-06-20 · Nanxing Meng, Qizao Wang, Bin Li, xiangyang xue

With rich temporal-spatial information, video-based person re-identification methods have shown broad prospects. Although tracklets can be easily obtained with ready-made tracking models, annotating identities is still e…

Person Re-IdentificationVideo-Based Person Re-Identification

Stepwise Metric Promotion for Unsupervised Video Person Re-Identification

2017-10-01 · ICCV 2017 10 · Zimo Liu, Dong Wang, Huchuan Lu

The intensive annotation cost and the rich but unlabeled data contained in videos motivate us to propose an unsupervised video-based person re-identification (re-ID) method. We start from two assumptions: 1) different vi…

Person Re-IdentificationRetrievalVideo-Based Person Re-Identification

Unsupervised Person Re-Identification with Wireless Positioning under Weak Scene Labeling

2021-10-29 · Yiheng Liu, Wengang Zhou, Qiaokang Xie, Houqiang Li

Existing unsupervised person re-identification methods only rely on visual clues to match pedestrians under different cameras. Since visual data is essentially susceptible to occlusion, blur, clothing changes, etc., a pr…

Graph Neural NetworkPerson Re-IdentificationScene LabelingUnsupervised Person Re-Identification

Unsupervised Person Re-identification via Softened Similarity Learning

2020-04-07 · CVPR 2020 6 · Yutian Lin, Lingxi Xie, Yu Wu, Chenggang Yan 외

Person re-identification (re-ID) is an important topic in computer vision. This paper studies the unsupervised setting of re-ID, which does not require any labeled information and thus is freely deployed to new scenarios…

ClusteringGeneral ClassificationPerson Re-IdentificationQuantization+1

Hard Samples Rectification for Unsupervised Cross-domain Person Re-identification

2021-06-14 · Chih-Ting Liu, Man-Yu Lee, Tsai-Shien Chen, Shao-Yi Chien

Person re-identification (re-ID) has received great success with the supervised learning methods. However, the task of unsupervised cross-domain re-ID is still challenging. In this paper, we propose a Hard Samples Rectif…

ClusteringPerson Re-IdentificationUnsupervised Domain AdaptationUnsupervised Person Re-Identification