COCAS: A Large-Scale Clothes Changing Person Dataset for Re-Identification

Yu, Shijie; Li, Shihua; Chen, Dapeng; Zhao, Rui; Yan, Junjie; Qiao, Yu

doi:10.1109/cvpr42600.2020.00346

Cited by 73 publications

(38 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing person search works mainly focus on several aspects, e.g., identity-driven detection [9,34], multi-scale learning [18,16], and partial matching [5,51]. Although several works [47,45,29] in the re-ID task have made early exploration on the clothchanging issue, it has not been studied fully to date. Moreover, few works have studied this problem in person search, especially the media scenes.…”

Section: Head Graph Body Graph Updated Graphmentioning

confidence: 99%

“…Cloth-changing person re-ID is a new rising challenging research topic that aims at retrieving pedestrians whose clothes are changed. Several works [14,45,47,25,10,30] have contributed to this field. Most of them focus on body shape or contour sketch, but these cues are not robust enough to view and posture variations.…”

Section: Cloth-changing Person Re-identificationmentioning

confidence: 99%

See 1 more Smart Citation

Head and Body: Unified Detector and Graph Network for Person Search in Media

Shu¹,

Tao²,

Qiao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Person search in media has seen increasing potential in Internet applications, such as video clipping and character collection. This task is common but overlooked by previous person search works which focus on surveillance scenes. The media scenarios have some different challenges from surveillance scenes. For example, a person may change his clothes frequently. To alleviate this issue, this paper proposes a Unified Detector and Graph Network (UDGNet) for person search in media. UDGNet is the first person search framework to detect and re-identify the human body and head simultaneously. Specifically, it first builds two branches based on a unified network to detect the human body and head, then the detected body and head are used for re-identification. This dual-task approach can significantly enhance discriminative learning. To tackle the cloth-changing issue, UDGNet builds two graphs to explore reliable links among cloth-changing samples and utilizes a graph network to learn better embeddings. This design effectively enhances the robustness of person search to cloth-changing challenges. Besides, we demonstrate that UDGNet can be implemented with both anchor-based and anchor-free person search frameworks and further achieve performance improvement. This paper also contributes a large-scale dataset for Person Search in Media (PSM), which provides both body and head annotations. It is by far the largest dataset for person search in media. Experiments show that UDGNet improves the anchor-free model AlignPS by 12.1% in mAP. Meanwhile, it shows good generalization across surveillance and longterm scenarios. The dataset and code will be available at : https://github.com/shuxjweb/PSM.git.

show abstract

Section: Head Graph Body Graph Updated Graphmentioning

confidence: 99%

Section: Cloth-changing Person Re-identificationmentioning

confidence: 99%

Head and Body: Unified Detector and Graph Network for Person Search in Media

Shu¹,

Tao²,

Qiao³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Therefore, NKUP data set covers more scenarios than LTCC 20 data sets, being beneficial for fair comparison on different cross‐clothes re‐ID models. What's more important, it takes a long period of time for the collection of NKUP data set, basically including all the clothing changes of people at all seasons, which is what COCAS 19 lacks(the data in COCAS was collected in 4 days). PRCC is the most similar publicly available data set with NKUP.…”

Section: Related Workmentioning

confidence: 99%

“…Same to Celebrities‐reID, 17 PRCC, 18 COCAS, 19 and LTCC, 20 NKUP proposed by us is an image‐based data set. To illustrate the necessary of NKUP data set for person re‐ID field, we analyze the difference between NKUP data set and other cross‐clothes data sets as follows.…”

Section: Related Workmentioning

confidence: 99%

A benchmark for clothes variation in person re‐identification

Wang

Chen

et al. 2020

Int J Intell Syst

View full text Add to dashboard Cite

Person re-identification (re-ID) has drawn attention significantly in the computer vision society due to its application and research significance. It aims to retrieve a person of interest across different camera views. However, there are still several factors that hinder the applications of person re-ID. In fact, most common data sets either assume that pedestrians do not change their clothing across different camera views or are taken under constrained environments. Those constraints simplify the person re-ID task and contribute to early development of person re-ID, yet a person has a great possibility to change clothes in real life. To facilitate the research toward conquering those issues, this paper mainly introduces a new benchmark data set for person reidentification. To the best of our knowledge, this data set is currently the most diverse for person re-identification. It contains 107 persons with 9,738 images, captured in 15 indoor/outdoor scenes from September 2019 to December 2019, varying according to viewpoints, lighting, resolutions, human pose, seasons, backgrounds, and clothes especially. We hope that this benchmark data set will encourage further research on person re-identification with clothes variation. Moreover, we also perform extensive analyses on this data set using several

show abstract

“…It is worth noting that many silhouette-based methods assume the whole human body as a unit to establish the spatiotemporal representations [10]. Further, gait recognition methods suffer from the insufficiency of the training data because the acquisition of the labeled gait images is difficult and expensive in practical scenarios because of lots of occlusion [11]and dressing [12]. Therefore, the numerous unlabeled gait images cannot be utilized for training the gait model even if they potentially contain rich information.…”

Section: Introductionmentioning

confidence: 99%

Selfgait: A Spatiotemporal Representation Learning Method for Self-Supervised Gait Recognition

Liu

Zeng

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Gait recognition plays a vital role in human identification since gait is a unique biometric feature that can be perceived at a distance. Although existing gait recognition methods can learn gait features from gait sequences in different ways, the performance of gait recognition suffers from insufficient labeled data, especially in some practical scenarios associated with short gait sequences or various clothing styles. It is unpractical to label the numerous gait data. In this work, we propose a self-supervised gait recognition method, termed SelfGait, which takes advantage of the massive, diverse, unlabeled gait data as a pre-training process to improve the representation abilities of spatiotemporal backbones. Specifically, we employ the horizontal pyramid mapping (HPM) and micro-motion template builder (MTB) as our spatiotemporal backbones to capture the multi-scale spatiotemporal representations. Experiments on CASIA-B and OU-MVLP benchmark gait datasets demonstrate the effectiveness of the proposed SelfGait compared with four state-of-the-art gait recognition methods. The source code has been released at https://github.com/EchoItLiu/SelfGait.

show abstract

COCAS: A Large-Scale Clothes Changing Person Dataset for Re-Identification

Cited by 73 publications

References 37 publications

Head and Body: Unified Detector and Graph Network for Person Search in Media

Head and Body: Unified Detector and Graph Network for Person Search in Media

A benchmark for clothes variation in person re‐identification

Selfgait: A Spatiotemporal Representation Learning Method for Self-Supervised Gait Recognition

Contact Info

Product

Resources

About