Weakly Supervised Person Search with Region Siamese Networks

Han, Chuchu; Su, Kuo-Lan; Yu, Dongdong; Yuan, Zehuan; Gao, Changxin; Yang, Yi; Wang, Changhu

doi:10.1109/iccv48922.2021.01179

Cited by 20 publications

(15 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [20,24,38], group context was used by graph matching. In [35] and [12], context was employed in an implicit way by using memory units in the weakly-supervised setting.…”

Section: Related Workmentioning

confidence: 99%

“…However, the person search images naturally contains much richer information, including the labeled persons, unlabeled persons and complete background, which could provide complementary information for re-ID learning. Inspired by this, some prior works have been proposed to explore the role of context information in person search [12,35] in an implicit and weakly supervised way. Group context has also been explored in several works by graph matching [20,24,37],…”

Section: Insufficient Use Of Person Search Datamentioning

confidence: 99%

“…Group re-ID methods [32,37,43] usually enhance the re-ID embeddings of the target person by incorporating the features of neighboring persons. Motivated by the above facts and owing to the setting of person search (i.e., a holistic image including multiple persons is provided), several attempts [1,12,23,24] have recently been made to learn the underlining context information beyond the detected person regions. They typically exploit two types of context information, i.e., scene and group.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, scene context is used in [1,23] to help identify the target via measuring the correspondence between the detected box of the query and the scene in the gallery. Group context is often mined in a pair-wise fashion, e.g., siamese networks are developed in [12,24] to find the potential co-travelers; [20,24,38] attempt to achieve the globally optimized matching based on the input pairs. However, most existing methods resort to either scene or group context, while both types of context make their own contributions to the final performance, as a person is not only related to the global scene, but also associated with the local neighbors.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

MovieNet-PS: A Large-Scale Person Search Dataset in the Wild

Zheng¹,

Qin²,

Yan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Person search aims to jointly localize and identify a query person from natural, uncropped images, which has been actively studied in the computer vision community over the past few years. In this paper, we delve into the rich context information globally and locally surrounding the target person, which we refer to scene and group context, respectively. Unlike previous works that treat the two types of context individually, we exploit them in a unified globallocal context network (GLCNet) with the intuitive aim of feature enhancement. Specifically, re-ID embeddings and context features are enhanced simultaneously in a multistage fashion, ultimately leading to enhanced, discriminative features for person search. We conduct the experiments on two person search benchmarks (i.e., CUHK-SYSU and PRW) as well as extend our approach to a more challenging setting (i.e., character search on MovieNet). Extensive experimental results demonstrate the consistent improvement of the proposed GLCNet over the state-of-the-art methods on the three datasets. Our source codes, pre-trained models, and the new setting for character search are available at: https://github.com/ZhengPeng7/GLCNet.

show abstract

“…In [20,24,38], group context was used by graph matching. In [35] and [12], context was employed in an implicit way by using memory units in the weakly-supervised setting.…”

Section: Related Workmentioning

confidence: 99%

Section: Insufficient Use Of Person Search Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

MovieNet-PS: A Large-Scale Person Search Dataset in the Wild

Zheng¹,

Qin²,

Yan³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…However, these supervised methods may suffer from significant performance degradation on unseen domains due to domain gaps. To address this problem, several recent works [40,20] propose the weakly supervised person search (WSPS) setting without accessible ID annotations, shown in Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

Domain Adaptive Person Search

Li¹,

Yan²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Person search is a challenging task which aims to achieve joint pedestrian detection and person re-identification (ReID). Previous works have made significant advances under fully and weakly supervised settings. However, existing methods ignore the generalization ability of the person search models. In this paper, we take a further step and present Domain Adaptive Person Search (DAPS), which aims to generalize the model from a labeled source domain to the unlabeled target domain. Two major challenges arises under this new setting: one is how to simultaneously solve the domain misalignment issue for both detection and ReID tasks, and the other is how to train the ReID subtask without reliable detection results on the target domain. To address these challenges, we propose a strong baseline framework with two dedicated designs. 1) We design a domain alignment module including image-level and task-sensitive instance-level alignments, to minimize the domain discrepancy. 2) We take full advantage of the unlabeled data with a dynamic clustering strategy, and employ pseudo bounding boxes to support ReID and detection training on the target domain. With the above designs, our framework achieves 34.7% in mAP and 80.6% in top-1 on PRW dataset, surpassing the direct transferring baseline by a large margin. Surprisingly, the performance of our unsupervised DAPS model even surpasses some of the fully and weakly supervised methods. The code is available at https://github.com/caposerenity/DAPS.

show abstract

Domain Adaptive Person Search

Yan

Wang

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Weakly Supervised Person Search with Region Siamese Networks

Cited by 20 publications

References 33 publications

MovieNet-PS: A Large-Scale Person Search Dataset in the Wild

MovieNet-PS: A Large-Scale Person Search Dataset in the Wild

Domain Adaptive Person Search

Domain Adaptive Person Search

Contact Info

Product

Resources

About