Similarity Learning with Spatial Constraints for Person Re-identification

Chen, Dapeng; Yuan, Zejian; Chen, Badong; Zheng, Nanning

doi:10.1109/cvpr.2016.142

Cited by 304 publications

(172 citation statements)

References 27 publications

Supporting

Mentioning

171

Contrasting

Order By: Relevance

“…In Table 1 only SS-SVM [16] is a metric that tries to model the transform modal for each individual person; however, it never paid attention to acquire resistance against impostors and thus has 19.21% lower rank@1 accuracy than IRM3 + CVI ( = 15). Though IRM3 has successful results, still it has 1.36% lower rank@1 than SCSP [38]. Obviously, VIPeR has large pose, misalignment, and body parts displacement issues which are specifically not addressed in our work and, thus, is necessarily needed to improve the matching and results largely.…”

Section: Results On Vipermentioning

confidence: 99%

Impostor Resilient Multimodal Metric Learning for Person Reidentification

Syed

Han

et al. 2018

Advances in Multimedia

View full text Add to dashboard Cite

In person reidentification distance metric learning suffers a great challenge from impostor persons. Mostly, distance metrics are learned by maximizing the similarity between positive pair against impostors that lie on different transform modals. In addition, these impostors are obtained from Gallery view for query sample only, while the Gallery sample is totally ignored. In real world, a given pair of query and Gallery experience different changes in pose, viewpoint, and lighting. Thus, impostors only from Gallery view can not optimally maximize their similarity. Therefore, to resolve these issues we have proposed an impostor resilient multimodal metric (IRM3). IRM3 is learned for each modal transform in the image space and uses impostors from both Probe and Gallery views to effectively restrict large number of impostors. Learned IRM3 is then evaluated on three benchmark datasets, VIPeR, CUHK01, and CUHK03, and shows significant improvement in performance compared to many previous approaches.

show abstract

Section: Results On Vipermentioning

confidence: 99%

Impostor Resilient Multimodal Metric Learning for Person Reidentification

Syed

Han

et al. 2018

Advances in Multimedia

View full text Add to dashboard Cite

show abstract

“…A growing number of Deep learning based methods are proposed to address cross-view person Re-Id in two main aspects: feature extraction and metric learning. he first category of methods [7,92,58,89,1,68,42] aims to generate effective discriminative representations via learning common or relevant visual features from cross-view samples to combat the view variations. The other category of approaches [10,39,43,41,44,107,3,96,37] employ a variety of different hand-crafted visual features such as color histogram, local maximal occurrence and local binary patterns to learn a similarity metric to measure the visual similarity between samples.…”

Section: Results Gallerymentioning

confidence: 99%

PAC-GAN: An effective pose augmentation scheme for unsupervised cross-view person re-identification

et al. 2020

View full text Add to dashboard Cite

Person re-identification (person Re-Id) aims to retrieve the pedestrian images of a same person that captured by disjoint and non-overlapping cameras. Lots of researchers recently focuse on this hot issue and propose deep learning based methods to enhance the recognition rate in a supervised or unsupervised manner. However, two limitations that cannot be ignored: firstly, compared with other image retrieval benchmarks, the size of existing person Re-Id datasets are far from meeting the requirement, which cannot provide sufficient pedestrian samples for the training of deep model; secondly, the samples in existing datasets do not have sufficient human motions or postures coverage to provide more priori knowledges for learning. In this paper, we introduce a novel unsupervised pose augmentation cross-view person Re-Id scheme called PAC-GAN to overcome these limitations. We firstly present the formal definition of cross-view pose augmentation and then propose the framework of PAC-GAN that is a novel conditional generative adversarial network (CGAN) based approach to improve the performance of unsupervised corss-view person Re-Id. Specifically, The pose generation model in PAC-GAN called CPG-Net is to generate enough quantity of pose-rich samples from original image and skeleton samples. The pose augmentation dataset is produced by combining the synthesized poserich samples with the original samples, which is fed into the corss-view person Re-Id model named Cross-GAN. Besides, we use weight-sharing strategy in the CPG-Net to improve the quality of new generated samples. To the best of our knowledge, we are the first try to enhance the unsupervised cross-view person Re-Id by pose augmentation, and the results of extensive experiments show that the proposed scheme can combat the state-of-the-arts.

show abstract

“…However, the above metric learning methods just focus on a holistic metric, which discard the geometric structure of human objects and thus affect the discriminative power. To deal with the issue effectively, considering a relatively stable space distribution of human body parts such as head, torso, and legs, Chen et al [50] propose spatially constrained similarity learning using polynomial feature map (SCSP) for human re-id. The proposed method, which combines a global similarity metric for the whole human body image region and multiple local similarity metrics for associating local human body parts regions using multiple visual cues, executes human matching across cameras based on multiple polynomial-kernel feature maps to represent human image pairs, which aims to learn a similarity function that could yield high score so as to measure the similarity between human image descriptors across cameras.…”

Section: Distance Metric Learningmentioning

confidence: 99%

“…To cope with this problem, Kuo et al [54] adopt multiple instances learning (MIL) to learn an appearance affinity model, which is then integrated with the spatial-temporal information to train an improved intercamera track association framework to tackle the target Fig. 12 Illustration of the similarity learning using spatial constraints based on polynomial-kernel feature map [50] Symbols √ and × mean whether CLM/GM based tracking is used or not handover tasks across cameras. In addition, people often walk in groups in crowded scenes, thus group information is also applied to appearance matching across cameras.…”

Section: Supervised Learning-based Clmmentioning

confidence: 99%

“…In order to mitigate cross-view variations and better identify more humans in human re-id, recent approaches [43,[45][46][47][48][49][50] are focused on learning an optimal metric model that aims to making features associated with the same human to be closer than features associated with different human objects. It is essential to learn a linear transformation that achieves a mapping from the original feature space to a new feature space so as to effectively execute human re-id.…”

Section: Distance Metric Learningmentioning

confidence: 99%

See 1 more Smart Citation

Human tracking over camera networks: a review

Hou

Wan

Hwang

et al. 2017

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

In recent years, automated human tracking over camera networks is getting essential for video surveillance. The tasks of tracking human over camera networks are not only inherently challenging due to changing human appearance, but also have enormous potentials for a wide range of practical applications, ranging from security surveillance to retail and health care. This review paper surveys the most widely used techniques and recent advances for human tracking over camera networks. Two important functional modules for the human tracking over camera networks are addressed, including human tracking within a camera and human tracking across nonoverlapping cameras. The core techniques of human tracking within a camera are discussed based on two aspects, i.e., generative trackers and discriminative trackers. The core techniques of human tracking across non-overlapping cameras are then discussed based on the aspects of human re-identification, camera-link model-based tracking and graph model-based tracking. Our survey aims to address existing problems, challenges, and future research directions based on the analyses of the current progress made toward human tracking techniques over camera networks.

show abstract

Similarity Learning with Spatial Constraints for Person Re-identification

Cited by 304 publications

References 27 publications

Impostor Resilient Multimodal Metric Learning for Person Reidentification

Impostor Resilient Multimodal Metric Learning for Person Reidentification

PAC-GAN: An effective pose augmentation scheme for unsupervised cross-view person re-identification

Human tracking over camera networks: a review

Contact Info

Product

Resources

About