Learning 3D Shape Feature for Texture-insensitive Person Re-identification

Chen, Jiaxing; Jiang, Xinyang; Wang, Fudong; Zhang, Jun; Zheng, Feng; Sun, Xing; Zheng, Wei‐Shi

doi:10.1109/cvpr46437.2021.00805

Cited by 56 publications

(23 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HACNN [31], PCB [40], and IANet [20]) and six clothes-changing re-id methods (i.e. SPT+ASE [49], GI-ReID [28], CESD [35], RCSANet [25], 3DSL [6], and FSAM [18]) on LTCC and PRCC in Tab. 2.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…To this end, [52,55] attempts to use disentangled representation learning to decouple appearance and structural information from RGB images, and considers structural information as clothes-irrelevant features. In contrast, other researchers attempt to use multi-modality information (e.g., skeletons [35], silhouettes [18,28], radio signals [7], contour sketches [49], or 3D shape [6]) to model body shape and extract clothesirrelevant features. However, the training of disentangled representation learning is time-consuming, and multimodality-based methods need additional models or equipment to extract multi-modality information.…”

Section: Related Workmentioning

confidence: 99%

“…Most current works [6,18,24,26,35,49] mainly focus on image-based settings and only a few works [7,10,51] focus on video-based settings. Besides, there are some publicly available clothes-changing person re-id datasets, e.g., PRCC [49], LTCC [35], and Celeb-reID [24,26], but all of them are image-based datasets.…”

Section: Related Workmentioning

confidence: 99%

“…The reason is that the human brain can decouple and utilize clothes-irrelevant features, e.g., face, hairstyle, body shape, and gait. To avoid the interference of clothes, some clothes-changing re-id methods [6,18] and gait recognition methods [4,52] model body shape and gait from multimodality inputs (e.g., skeletons [35], silhouettes [4], radio signals [7], contour sketches [49], and 3D shape [6]) or by disentangled representation learning [52]. However, multimodality-based methods need additional models or equipment to capture multi-modality information, and learning disentangled representations is usually time-consuming.…”

Section: Introductionmentioning

confidence: 99%

“…Actually, the original RGB modality contains rich clothes-irrelevant information which is largely underutilized by the current methods. As for some clothes-changing re-id methods [6,35], although they use a strong backbone (i.e. ResNet [15]) to extract features from the original images, without a properly designed loss function, the learned feature map only focuses on some simple clothes-irrelevant information, e.g., face (see Fig.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Clothes-Changing Person Re-identification with RGB Modality Only

Gu¹,

Chen²,

Ma³

et al. 2022

Preprint

View full text Add to dashboard Cite

The key to address clothes-changing person reidentification (re-id) is to extract clothes-irrelevant features, e.g., face, hairstyle, body shape, and gait. Most current works mainly focus on modeling body shape from multimodality information (e.g., silhouettes and sketches), but do not make full use of the clothes-irrelevant information in the original RGB images. In this paper, we propose a Clothes-based Adversarial Loss (CAL) to mine clothesirrelevant features from the original RGB images by penalizing the predictive power of re-id model w.r.t. clothes. Extensive experiments demonstrate that using RGB images only, CAL outperforms all state-of-the-art methods on widely-used clothes-changing person re-id benchmarks. Besides, compared with images, videos contain richer appearance and additional temporal information, which can be used to model proper spatiotemporal patterns to assist clothes-changing re-id. Since there is no publicly available clothes-changing video re-id dataset, we contribute a new dataset named CCVID and show that there exists much room for improvement in modeling spatiotemporal information. The code and new dataset are available at: https: //github.com/guxinqian/Simple-CCReID.

show abstract

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Clothes-Changing Person Re-identification with RGB Modality Only

Gu¹,

Chen²,

Ma³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

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

Multi-view Geometry Distillation for Cloth-Changing Person ReID

Liu²,

Lu³

et al. 2022

Pattern Recognition and Computer Vision

View full text Add to dashboard Cite

Learning 3D Shape Feature for Texture-insensitive Person Re-identification

Cited by 56 publications

References 41 publications

Clothes-Changing Person Re-identification with RGB Modality Only

Clothes-Changing Person Re-identification with RGB Modality Only

A benchmark for clothes variation in person re‐identification

Multi-view Geometry Distillation for Cloth-Changing Person ReID

Contact Info

Product

Resources

About