A benchmark for clothes variation in person re‐identification

Wang, Kai; Ma, Zhi; Chen, Shiyan; Yang, Jinni; Zhou, Keke; Li, Tao

doi:10.1002/int.22276

Cited by 30 publications

(17 citation statements)

References 76 publications

(141 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A few recent person re-id works try to tackle [17,26,32,38,41,42,47] the long-term clothes change situations by fully-supervised training. Their main motivation is looking for additional supervision for the general appearance features (e.g., clothes, color), to help the model to learn the cross-clothes invariance.…”

Section: Long-term Person Re-identificationmentioning

confidence: 99%

“…This limitation has led to an emerging research interest on long-term person re-id with focus on clothes changes [15,17,26,32,38,41,42,45,47]. As it is extremely difficult to collect and annotate the person identity labels under unconstrained clothes change, most of previous long-term re-id works resort to creating synthetic datasets (e.g., VC-Clothes [39]) or small scale real datasets (e.g., Real28 [39] with 28 person identities, NKUP [41] with 107 person identities). An exception is DeepChange [45], the latest, largest, and realistic person re-id benchmark with clothes change, which however was established at an exhaustive cost.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Long-Term Person Re-Identification with Clothes Change

Li¹,

Xu²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

We investigate unsupervised person re-identification (reid) with clothes change, a new challenging problem with more practical usability and scalability to real-world deployment. Most existing re-id methods artificially assume the clothes of every single person to be stationary across space and time. This condition is mostly valid for short-term re-id scenarios since an average person would often change the clothes even within a single day. To alleviate this assumption, several recent works have introduced the clothes change facet to re-id, with a focus on supervised learning person identity discriminative representation with invariance to clothes changes. Taking a step further towards this long-term re-id direction, we further eliminate the requirement of person identity labels, as they are significantly more expensive and more tedious to annotate in comparison to short-term person re-id datasets. Compared to conventional unsupervised short-term re-id, this new problem is drastically more challenging as different people may have similar clothes whilst the same person can wear multiple suites of clothes over different locations and times with very distinct appearance. To overcome such obstacles, we introduce a novel Curriculum Person Clustering (CPC) method that can adaptively regulate the unsupervised clustering criterion according to the clustering confidence. Experiments on three long-term person re-id datasets show that our CPC outperforms the state-of-the-art unsupervised re-id methods and even closely matches the supervised re-id models.

show abstract

Section: Long-term Person Re-identificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Unsupervised Long-Term Person Re-Identification with Clothes Change

Li¹,

Xu²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Gesture recognition is mainly divided into image‐ and sensor‐based recognition, which originated from the biological motion perception model designed by Johansson in 1973, 4 tracking the movement of biological joints and limbs through a camera or sensor to perceive the biological motion process 5 …”

Section: Related Workmentioning

confidence: 99%

A fully connected deep learning approach to upper limb gesture recognition in a secure FES rehabilitation environment

Liu

Jiang

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

Stroke is one of the leading causes of death and disability in the world. The rehabilitation of Patients' limb functions has great medical value, for example, the therapy of functional electrical stimulation (FES) systems, but suffers from effective rehabilitation evaluation. In this paper, six gestures of upper limb rehabilitation were monitored and collected using microelectromechanical systems sensors, where data stability was guaranteed using data preprocessing methods, that is, deweighting, interpolation, and feature extraction. A fully connected neural network has been proposed investigating the effects of different hidden layers, and determining its activation functions and optimizers. Experiments have depicted that a three‐hidden‐layer model with a softmax function and an adaptive gradient descent optimizer can reach an average gesture recognition rate of 97.19%. A stop mechanism has been used via recognition of dangerous gesture to ensure the safety of the system, and the lightweight cryptography has been used via hash to ensure the security of the system. Comparison to the classification models, for example, k‐nearest neighbor, logistic regression, and other random gradient descent algorithms, was conducted to verify the outperformance in recognition of upper limb gesture data. This study also provides an approach to creating health profiles based on large‐scale rehabilitation data and therefore consequent diagnosis of the effects of FES rehabilitation.

show abstract

“…In Reference, 34 CamStyle serves as a data augmentation approach that smooths the camera‐style disparities. In Reference, 35 NKUP is a benchmark data set for clothes variation in person re‐id, which is proposed to encourage further research on person re‐id with clothes variation. As for the problem of unsupervised person re‐id whose core is to solve the problem of insufficient person re‐id data set, Wu et al 36 regard each image as a single class, and propose a nonparametric softmax classifier to train CNN.…”

Section: Related Workmentioning

confidence: 99%

Topology and channel affinity reinforced global attention for person re‐identification

Wang

Gao

Xin

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Person re‐identification (re‐id), with the goal to recognize persons from images captured by nonoverlapping cameras, is a challenging topic in computer vision. It has been studied extensively in recent years, and the attention mechanism is widely applied in person re‐id. But many works mainly focus on extracting discriminative features from local saliency regions, while ignoring some potentially global information between whole‐body features and body‐part features. In this study, we first proposed two effective global information for extracting discriminative features: spatial topology information (STI) and channel affinity information (CAI). On this basis, we further propose a Multi‐information Fusion reinforced Global Attention (MIFGA) module which can effectively fuse a variety of information and utilize more comprehensive information to guide the learning of attention, so as to obtain pedestrian features that are conducive to clustering. Specifically, the proposed MIFGA module includes spatial attention (MIFGA‐S) and channel attention (MIFGA‐C). MIFGA‐S mainly utilizes local feature semantic information and STI to guide the learning of spatial attention. Furthermore, to mine the potential topology information in original feature maps, the self‐learning graph convolution network is proposed. MIFGA‐C fuses channel semantic information and CAI to guide the learning of channel attention. Extensive ablation studies demonstrate that our proposed MIFGA significantly enhances the baseline model and achieves a competitive performance compared with the state‐of‐the‐art person re‐id methods on standard data sets Market‐1501, DukeMTMC‐reID, and CUHK03.

show abstract

A benchmark for clothes variation in person re‐identification

Cited by 30 publications

References 76 publications

Unsupervised Long-Term Person Re-Identification with Clothes Change

Unsupervised Long-Term Person Re-Identification with Clothes Change

A fully connected deep learning approach to upper limb gesture recognition in a secure FES rehabilitation environment

Topology and channel affinity reinforced global attention for person re‐identification

Contact Info

Product

Resources

About