Person Re-Identification Ranking Optimisation by Discriminant Context Information Analysis

García, Jorge; Martinel, Niki; Micheloni, Christian; Gardel, Alfredo

doi:10.1109/iccv.2015.154

Cited by 80 publications

(48 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Incorporating G2G affinities to improve the initial ranking of gallery images is considered as a re-ranking problem. There were some previous attempts on re-ranking with affinities between top-ranked gallery images [45,10,14,37,38]. Most of these re-ranking approaches utilized the k-nearest neighbors of the gallery image.…”

Section: Introductionmentioning

confidence: 99%

Deep Group-Shuffling Random Walk for Person Re-identification

Shen¹,

Xiao

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

143

116

View full text Add to dashboard Cite

Person re-identification aims at finding a person of interest in an image gallery by comparing the probe image of this person with all the gallery images. It is generally treated as a retrieval problem, where the affinities between the probe image and gallery images (P2G affinities) are used to rank the retrieved gallery images. However, most existing methods only consider P2G affinities but ignore the affinities between all the gallery images (G2G affinity). Some frameworks incorporated G2G affinities into the testing process, which is not end-to-end trainable for deep neural networks. In this paper, we propose a novel group-shuffling random walk network for fully utilizing the affinity information between gallery images in both the training and testing processes. The proposed approach aims at end-to-end refining the P2G affinities based on G2G affinity information with a simple yet effective matrix operation, which can be integrated into deep neural networks. Feature grouping and group shuffle are also proposed to apply rich supervisions for learning better person features. The proposed approach outperforms state-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets by large margins, which demonstrate the effectiveness of our approach.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Group-Shuffling Random Walk for Person Re-identification

Shen¹,

Xiao

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

143

116

View full text Add to dashboard Cite

show abstract

“…To study person re-ID with the manifoldbased affinity learning, Bai et al [4] introduce a manifoldpreserving algorithm plunging into existing re-ID algorithms to enhance the performance. Re-ranking which exploits the relationships amongst initial ranking list in person re-ID has been studied to improve the performance [60], [15], [14]. Finally, human feedback in-the-loop is required that provides an instant improvement to re-ID ranking on-the-fly [2], [48], [34].…”

Section: B Person Re-identificationmentioning

confidence: 99%

Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification

Huang

et al. 2019

IEEE Trans. on Image Process.

118

View full text Add to dashboard Cite

Sufficient training data normally is required to train deeply learned models. However, due to the expensive manual process for labelling large number of images (i.e., annotation), the amount of available training data (i.e., real data) is always limited. To produce more data for training a deep network, Generative Adversarial Network (GAN) can be used to generate artificial sample data (i.e., generated data). However, the generated data usually does not have annotation labels. To solve this problem, in this paper, we propose a virtual label called Multi-pseudo Regularized Label (MpRL) and assign it to the generated data. With MpRL, the generated data will be used as the supplementary of real training data to train a deep neural network in a semi-supervised learning fashion. To build the corresponding relationship between the real data and generated data, MpRL assigns each generated data a proper virtual label which reflects the likelihood of the affiliation of the generated data to pre-defined training classes in the real data domain. Unlike the traditional label which usually is a single integral number, the virtual label proposed in this work is a set of weight-based values each individual of which is a number in (0,1] called multi-pseudo label and reflects the degree of relation between each generated data to every pre-defined class of real data.A comprehensive evaluation is carried out by adopting two state-of-the-art convolutional neural networks (CNNs) in our experiments to verify the effectiveness of MpRL. Experiments demonstrate that by assigning MpRL to generated data, we can further improve the person re-ID performance on five re-ID datasets, i.e., Market-1501, DukeMTMC-reID, CUHK03, VIPeR, and CUHK01. The proposed method obtains +6.29%, +6.30%, +5.58%, +5.84%, and +3.48% improvements in rank-1 accuracy over a strong CNN baseline on the five datasets respectively, and outperforms state-of-the-art methods.

show abstract

“…Re-ranking Scheme. Re-ranking has been successfully studied in unimodal retrieval task such as person re-ID [8,22,40,41], object retrieval [28,30] and text-based image search [11,38,39] to improve the accuracy. In these problems, retrieved candidates within initial rank list can be re-ordered as an additional refinement process.…”

Section: Related Workmentioning

confidence: 99%

Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking

Wang

Yang

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

125

View full text Add to dashboard Cite

A major challenge in matching images and text is that they have intrinsically different data distributions and feature representations. Most existing approaches are based either on embedding or classification, the first one mapping image and text instances into a common embedding space for distance measuring, and the second one regarding image-text matching as a binary classification problem. Neither of these approaches can, however, balance the matching accuracy and model complexity well. We propose a novel framework that achieves remarkable matching performance with acceptable model complexity. Specifically, in the training stage, we propose a novel Multi-modal Tensor Fusion Network (MTFN) to explicitly learn an accurate image-text similarity function with rank-based tensor fusion rather than seeking a common embedding space for each image-text instance. Then, during testing, we deploy a generic Cross-modal Re-ranking (RR) scheme for refinement without requiring additional training procedure. Extensive experiments on two datasets demonstrate that our MTFN-RR consistently achieves the state-of-the-art matching performance with much less time complexity. CCS CONCEPTS• Information systems → Multimedia and multimodal retrieval. Figure 1: Illustration of the embedding-based (top) and the classification-based methods (bottom) that are typically used for image-text matching.

show abstract

Person Re-Identification Ranking Optimisation by Discriminant Context Information Analysis

Cited by 80 publications

References 31 publications

Deep Group-Shuffling Random Walk for Person Re-identification

Deep Group-Shuffling Random Walk for Person Re-identification

Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification

Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking

Contact Info

Product

Resources

About