Attributes driven tracklet-to-tracklet person re-identification using latent prototypes space mapping

Su, Chi; Zhang, Shiliang; Yang, Fan; Zhang, Guangxiao; Gao, Wen; Davis, Larry S.

doi:10.1016/j.patcog.2017.01.006

Cited by 40 publications

(15 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To validate the performance of deep attributes, we test them on four popular person ReID datasets without combining with the local visual features. The experimental results show that deep attributes perform impressively, e.g., they significantly outperform many recent works combining both attributes and local features [31,32,33,34]. Note that, predicting and matching deep attributes make person ReID system significantly faster, because it no longer needs to extract and code local features, compute distance metric, and fuse with other features.…”

Section: Introductionmentioning

confidence: 90%

See 1 more Smart Citation

Deep Attributes Driven Multi-camera Person Re-identification

Zhang

Xing

et al. 2016

Computer Vision – ECCV 2016

Self Cite

308

196

View full text Add to dashboard Cite

Abstract. The visual appearance of a person is easily affected by many factors like pose variations, viewpoint changes and camera parameter differences. This makes person Re-Identification (ReID) among multiple cameras a very challenging task. This work is motivated to learn mid-level human attributes which are robust to such visual appearance variations. And we propose a semi-supervised attribute learning framework which progressively boosts the accuracy of attributes only using a limited number of labeled data. Specifically, this framework involves a three-stage training. A deep Convolutional Neural Network (dCNN) is first trained on an independent dataset labeled with attributes. Then it is fine-tuned on another dataset only labeled with person IDs using our defined triplet loss. Finally, the updated dCNN predicts attribute labels for the target dataset, which is combined with the independent dataset for the final round of fine-tuning. The predicted attributes, namely deep attributes exhibit superior generalization ability across different datasets. By directly using the deep attributes with simple Cosine distance, we have obtained surprisingly good accuracy on four person ReID datasets. Experiments also show that a simple distance metric learning modular further boosts our method, making it significantly outperform many recent works.

show abstract

Section: Introductionmentioning

confidence: 90%

“…1, attributes are more consistent for the same person and are more robust to the above mentioned variances. Some recent works hence have started to use attributes for person ReID [29,30,31,32,33,34]. Because human attributes are expensive for manual annotation, it is difficult to acquire enough training data for a large set of attributes.…”

Section: Introductionmentioning

confidence: 99%

Deep Attributes Driven Multi-camera Person Re-identification

Zhang

Xing

et al. 2016

Computer Vision – ECCV 2016

Self Cite

308

196

View full text Add to dashboard Cite

show abstract

“…Reference [36] tuned deep Re-ID network with additional semantic attributes. Reference [37] exploited the inter-attribute correlations to improve the representation. Reference [15] combined the semantic attribute learning process into the CNN framework.…”

Section: B Person Re-id With Semantic Attributesmentioning

confidence: 99%

Learning Sparse and Identity-Preserved Hidden Attributes for Person Re-Identification

Wang

Jiang

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Person re-identification (Re-ID) aims at matching person images captured in non-overlapping camera views. To represent person appearance, low-level visual features are sensitive to environmental changes, while high-level semantic attributes, such as "short-hair" or "long-hair", are relatively stable. Hence, researches have started to design semantic attributes to reduce the visual ambiguity. However, to train a prediction model for semantic attributes, it requires plenty of annotations, which are hard to obtain in practical large-scale applications. To alleviate the reliance on annotation efforts, we propose to incrementally generate Deep Hidden Attribute (DHA) based on baseline deep network for newly uncovered annotations. In particular, we propose an auto-encoder model that can be plugged into any deep network to mine latent information in an unsupervised manner. To optimize the effectiveness of DHA, we reform the auto-encoder model with additional orthogonal generation module, along with identity-preserving and sparsity constraints. 1) Orthogonally generating: In order to make DHAs different from each other, Singular Vector Decomposition (SVD) is introduced to generate DHAs orthogonally. 2) Identity-preserving constraint: The generated DHAs should be distinct for telling different persons, so we associate DHAs with person identities. 3) Sparsity constraint: To enhance the discriminability of DHAs, we also introduce the sparsity constraint to restrict the number of effective DHAs for each person. Experiments conducted on public datasets have validated the effectiveness of the proposed network. On two large-scale datasets, i.e., Market-1501 and DukeMTMC-reID, the proposed method outperforms the state-of-the-art methods.

show abstract

“…Person re-identification (Re-ID) has become an active research topic in the field of computer vision, because of its wide application in the video surveillance community. Given one single shot or multiple shots of a target, person Re-ID concerns the problem of matching the same person among a set of gallery candidates captured from the disjoint camera views [1][2][3][4]. It is a very challenging task due to noisy samples with mutual occlusion and background clutter that makes the large appearance variations across different camera views [5,6].…”

Section: Introductionmentioning

confidence: 99%

Deep self-paced learning for person re-identification

Zhou

Wang

Meng

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

Person re-identification (Re-ID) usually suffers from noisy samples with background clutter and mutual occlusion, which makes it extremely difficult to distinguish different individuals across the disjoint camera views. In this paper, we propose a novel deep selfpaced learning (DSPL) algorithm to alleviate this problem, in which we apply a self-paced constraint and symmetric regularization to help the relative distance metric training the deep neural network, so as to learn the stable and discriminative features for person Re-ID. Firstly, we propose a soft polynomial regularizer term which can derive the adaptive weights to samples based on both the training loss and model age. As a result, the high-confidence fidelity samples will be emphasized and the low-confidence noisy samples will be suppressed at early stage of the whole training process. Such a learning regime is naturally implemented under a self-paced learning (SPL) framework, in which samples weights are adaptively updated based on both model age and sample loss using an alternative optimization method. Secondly, we introduce a symmetric regularizer term to revise the asymmetric gradient back-propagation derived by the relative distance metric, so as to simultaneously minimize the intra-class distance and maximize the inter-class distance in each triplet unit. Finally, we build a part-based deep neural network, in which the features of different body parts are first discriminately learned in the lower convolutional layers and then fused in the higher fully connected layers.Experiments on several benchmark datasets have demonstrated the superior performance of our method as compared with the state-of-the-art approaches.

show abstract

Attributes driven tracklet-to-tracklet person re-identification using latent prototypes space mapping

Cited by 40 publications

References 41 publications

Deep Attributes Driven Multi-camera Person Re-identification

Deep Attributes Driven Multi-camera Person Re-identification

Learning Sparse and Identity-Preserved Hidden Attributes for Person Re-Identification

Deep self-paced learning for person re-identification

Contact Info

Product

Resources

About