paper-with-me

Papers

Exploring Visual Context for Weakly Supervised Person Search

2021-06-19 · Yichao Yan, Jinpeng Li, Shengcai Liao, Jie Qin, Bingbing Ni, Xiaokang Yang, Ling Shao

Person search has recently emerged as a challenging task that jointly addresses pedestrian detection and person re-identification. Existing approaches follow a fully supervised setting where both bounding box and identity annotations are available. However, annotating identities is labor-intensive, limiting the practicability and scalability of current frameworks. This paper inventively considers weakly supervised person search with only bounding box annotations. We proposed to address this novel task by investigating three levels of context clues (i.e., detection, memory and scene) in unconstrained natural images. The first two are employed to promote local and global discriminative capabilities, while the latter enhances clustering accuracy. Despite its simple design, our CGPS achieves 80.0% in mAP on CUHK-SYSU, boosting the baseline model by 8.8%. Surprisingly, it even achieves comparable performance with several supervised person search models. Our code is available at https://github.com/ljpadam/CGPS

📄 PDF Abstract BibTeX arXiv:2106.10506

Code (3)

ljpadam/CGPS 공식 구현 pytorch
2023-MindSpore-1/ms-code-119 mindspore
2023-MindSpore-4/Code16/tree/main/yanyichao/mindspore_CGPS-master mindspore

Tasks

ClusteringPedestrian DetectionPerson Re-IdentificationPerson Search

Similar Papers 제목 키워드 기반

CGUA: Context-Guided and Unpaired-Assisted Weakly Supervised Person Search

2022-03-27 · Chengyou Jia, Minnan Luo, Caixia Yan, Xiaojun Chang 외

Recently, weakly supervised person search is proposed to discard human-annotated identities and train the model with only bounding box annotations. A natural way to solve this problem is to separate it into detection and…

Person Search

Weakly Supervised Dataset Collection for Robust Person Detection

2020-03-27 · Munetaka Minoguchi, Ken Okayama, Yutaka Satoh, Hirokatsu Kataoka

To construct an algorithm that can provide robust person detection, we present a dataset with over 8 million images that was produced in a weakly supervised manner. Through labor-intensive human annotation, the person de…

Human Detection

Weakly supervised discriminative feature learning with state information for person identification

2020-02-27 · CVPR 2020 6 · Hong-Xing Yu, Wei-Shi Zheng

Unsupervised learning of identity-discriminative visual feature is appealing in real-world tasks where manual labelling is costly. However, the images of an identity can be visually discrepant when images are taken under…

Face RecognitionPerson IdentificationPerson Re-IdentificationPseudo Label+2

Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing

2021-12-01 · NeurIPS 2021 12 · Yan-Bo Lin, Hung-Yu Tseng, Hsin-Ying Lee, Yen-Yu Lin 외

The audio-visual video parsing task aims to temporally parse a video into audio or visual event categories. However, it is labor intensive to temporally annotate audio and visual events and thus hampers the learning of a…

Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd counting

2022-03-12 · Fusen Wang, Kai Liu, Fei Long, Nong Sang 외

Currently, for crowd counting, the fully supervised methods via density map estimation are the mainstream research directions. However, such methods need location-level annotation of persons in an image, which is time-co…

Crowd CountingWeakly-supervised Learning