Multiregion Bilinear Convolutional Neural Networks for Person Re-Identification

Ustinova, Evgeniya; Ganin, Yaroslav; Lempitsky, Victor

doi:10.48550/arxiv.1512.05300

Cited by 13 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…rank-1 rank-5 rank-10 rank-20 mAP DADM [34] 39.4 ---19.6 MBC [37] 45.56 67 76 82 26.11 SML [15] 45.16 68.12 76 84 -DLDA [40] 48.15 ---29.94 SL [4] 51.9 ---26.35 DNS [45] 55.43 ---29.87 LSTM [39] 61.6 ---35.3 S-CNN [38] 65.88 ---39.55 2Stream [53] 1.…”

Section: Methodsmentioning

confidence: 99%

Improving person re-identification by attribute and identity learning

Lin

Zheng

et al. 2019

Pattern Recognition

670

480

View full text Add to dashboard Cite

Person re-identification (re-ID) and attribute recognition share a common target at the pedestrian description. Their difference consists in the granularity. Attribute recognition focuses on local aspects of a person while person re-ID usually extracts global representations. Considering their similarity and difference, this paper proposes a very simple convolutional neural network (CNN) that learns a re-ID embedding and predicts the pedestrian attributes simultaneously. This multi-task method integrates an ID classification loss and a number of attribute classification losses, and back-propagates the weighted sum of the individual losses.Albeit simple, we demonstrate on two pedestrian benchmarks that by learning a more discriminative representation, our method significantly improves the re-ID baseline and is scalable on large galleries. We report competitive re-ID performance compared with the state-of-the-art methods on the two datasets.

show abstract

Section: Methodsmentioning

confidence: 99%

Improving person re-identification by attribute and identity learning

Lin

Zheng

et al. 2019

Pattern Recognition

670

480

View full text Add to dashboard Cite

show abstract

“…Person re-identification Feature extraction and metric learning [12,17] are two main components for person reidentification. The success of deep learning in image classification inspired lots of studies on person ReID [5,16,30,29,26,23,25,15,31]. The filter pairing neural network (FPNN) proposed by Li et al [16] jointly handles misalignment, transforms, occlusions and background clutters.…”

Section: Related Workmentioning

confidence: 99%

HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis

Liu

Zhao

Tian³

et al. 2017

2017 IEEE International Conference on Computer Vision (ICCV)

474

396

View full text Add to dashboard Cite

Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems. Despite that the convolutional neural networks are remarkable in learning discriminative features from images, the learning of comprehensive features of pedestrians for fine-grained tasks remains an open problem. In this study, we propose a new attentionbased deep neural network, named as HydraPlus-Net (HPnet), that multi-directionally feeds the multi-level attention maps to different feature layers. The attentive deep features learned from the proposed HP-net bring unique advantages: (1) the model is capable of capturing multiple attentions from low-level to semantic-level, and (2) it explores the multi-scale selectiveness of attentive features to enrich the final feature representations for a pedestrian image. We demonstrate the effectiveness and generality of the proposed HP-net for pedestrian analysis on two tasks, i.e. pedestrian attribute recognition and person reidentification. Intensive experimental results have been provided to prove that the HP-net outperforms the state-of-theart methods on various datasets.

show abstract

“…From the results in Table IX, it is clear that the proposed PDH method significantly outperforms most of deep learning based re-id methods in both rank-1 accuracy and mAP. Only the PDH (MQ avg) is slightly inferior to Multiregion Bilinear DML (MQ avg) [45] in mAP. Nevertheless, the advantage of our method lies in the binary signatures, which enable fast person re-id in large galleries.…”

Section: ) Comparison With the State-of-the-art Person Re-id Methodsmentioning

confidence: 93%

“…However, the VIPER and PRID-2011 are both comparatively small datasets. E. Ustinova et al [45] utilize bilinear pooling method based on Bilinear CNN for person re-id, which is implemented over multiregion for extracting more useful descriptors in the two large datasets CUHK 03 [7] and Market-1501 [10]. Chen et al [21] design a deep ranking framework to formulate the person reid task.…”

Section: B Deeply-learned Methods For Person Re-identificationmentioning

confidence: 99%

“…Then we compare with some state-of-the-art person reid methods based on deep learning, including Multi-region Bilinear Convolutional Neural Networks method [45], Person-Net method [68], Semi-supervised Deep Attribute Learning (SSDAL) method [69], Temporal Model Adaptation (TMA) method [70] and End-to-end Comparative Attention Network (CAN) method [71]. From the results in Table IX, it is clear that the proposed PDH method significantly outperforms most of deep learning based re-id methods in both rank-1 accuracy and mAP.…”

Section: ) Comparison With the State-of-the-art Person Re-id Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Part-Based Deep Hashing for Large-Scale Person Re-Identification

Zhu

Kong

Zheng

et al. 2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Large-scale is a trend in person re-identi- fication (re-id). It is important that real-time search be performed in a large gallery. While previous methods mostly focus on discriminative learning, this paper makes the attempt in integrating deep learning and hashing into one framework to evaluate the efficiency and accuracy for large-scale person re-id. We integrate spatial information for discriminative visual representation by partitioning the pedestrian image into horizontal parts. Specifically, Part-based Deep Hashing (PDH) is proposed, in which batches of triplet samples are employed as the input of the deep hashing architecture. Each triplet sample contains two pedestrian images (or parts) with the same identity and one pedestrian image (or part) of the different identity. A triplet loss function is employed with a constraint that the Hamming distance of pedestrian images (or parts) with the same identity is smaller than ones with the different identity. In the experiment, we show that the proposed PDH method yields very competitive re-id accuracy on the large-scale Market-1501 and Market-1501+500K datasets.

show abstract

Multiregion Bilinear Convolutional Neural Networks for Person Re-Identification

Cited by 13 publications

References 0 publications

Improving person re-identification by attribute and identity learning

Improving person re-identification by attribute and identity learning

HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis

Part-Based Deep Hashing for Large-Scale Person Re-Identification

Contact Info

Product

Resources

About