paper-with-me

홈 › Papers

Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification

2020-06-13 · Zhiyuan Chen, Annan Li, Shilu Jiang, Yunhong Wang

Video-based person re-identification (Re-ID) is an important computer vision task. The batch-hard triplet loss frequently used in video-based person Re-ID suffers from the Distance Variance among Different Positives (DVDP) problem. In this paper, we address this issue by introducing a new metric learning method called Attribute-aware Identity-hard Triplet Loss (AITL), which reduces the intra-class variation among positive samples via calculating attribute distance. To achieve a complete model of video-based person Re-ID, a multi-task framework with Attribute-driven Spatio-Temporal Attention (ASTA) mechanism is also proposed. Extensive experiments on MARS and DukeMTMC-VID datasets shows that both the AITL and ASTA are very effective. Enhanced by them, even a simple light-weighted video-based person Re-ID baseline can outperform existing state-of-the-art approaches. The codes has been published on https://github.com/yuange250/Video-based-person-ReID-with-Attribute-information.

📄 PDF Abstract BibTeX arXiv:2006.07597

Code (2)

yuange250/Video-based-person-ReID-with-Attribute-information 공식 구현 pytorch
wuyang1903220154/Video-based-person-ReID-with-Attribute-information pytorch

Tasks

AttributeMetric LearningPerson Re-IdentificationTripletVideo-Based Person Re-Identification

Methods 이 논문이 사용한 방법론

Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

Similar Papers 제목 키워드 기반

Video Person Re-identification using Attribute-enhanced Features

2021-08-16 · Tianrui Chai, ZhiYuan Chen, Annan Li, Jiaxin Chen 외

Video-based person re-identification (Re-ID) which aims to associate people across non-overlapping cameras using surveillance video is a challenging task. Pedestrian attribute, such as gender, age and clothing characteri…

AttributePerson Re-IdentificationTripletVideo-Based Person Re-Identification

Triplet Online Instance Matching Loss for Person Re-identification

2020-02-24 · Ye Li, Guangqiang Yin, Chunhui Liu, Xiaoyu Yang 외

Mining the shared features of same identity in different scene, and the unique features of different identity in same scene, are most significant challenges in the field of person re-identification (ReID). Online Instanc…

Person Re-IdentificationTriplet

Learning Incremental Triplet Margin for Person Re-identification

2018-12-17 · Yingying Zhang, Qiaoyong Zhong, Liang Ma, Di Xie 외

Person re-identification (ReID) aims to match people across multiple non-overlapping video cameras deployed at different locations. To address this challenging problem, many metric learning approaches have been proposed,…

Metric LearningPerson Re-IdentificationTriplet

Deep Identity-aware Transfer of Facial Attributes

2016-10-18 · Mu Li, WangMeng Zuo, David Zhang

This paper presents a Deep convolutional network model for Identity-Aware Transfer (DIAT) of facial attributes. Given the source input image and the reference attribute, DIAT aims to generate a facial image that owns the…

AttributeDenoisingFace HallucinationHallucination+1

Improving Deep Binary Embedding Networks by Order-aware Reweighting of Triplets

2018-04-17 · Jikai Chen, Hanjiang Lai, Libing Geng, Yan Pan

In this paper, we focus on triplet-based deep binary embedding networks for image retrieval task. The triplet loss has been shown to be most effective for the ranking problem. However, most of the previous works treat th…

Image RetrievalRetrievalTriplet