End-to-End Comparative Attention Networks for Person Re-Identification

  title={End-to-End Comparative Attention Networks for Person Re-Identification},
  author={Hao Liu and Jiashi Feng and Meibin Qi and Jianguo Jiang and Shuicheng Yan},
  journal={IEEE Transactions on Image Processing},
Person re-identification across disjoint camera views has been widely applied in video surveillance yet it is still a challenging problem. One of the major challenges lies in the lack of spatial and temporal cues, which makes it difficult to deal with large variations of lighting conditions, viewing angles, body poses, and occlusions. Recently, several deep-learning-based person re-identification approaches have been proposed and achieved remarkable performance. However, most of those… 

Multi-layer attention for person re-identification

A novel attention network which explores spatial attention in a convolutional neural network that pays attention to the spatial probabilities of local regions, but also takes the features in different levels into consideration.

SliceNet: Mask Guided Efficient Feature Augmentation for Attention-Aware Person Re-Identification

A novel SliceNet with efficient feature augmentation modules for open-world person re-identification and aims to learn self-alignment masks for discovering and exploiting the align-attention regions, combined with the attention free baseline network to characterize global features.

Person re-identification in images with deep learning

This thesis proposes a CNN-based person re-identification framework composed of an identity classification branch and of an attribute recognition branch, and a novel listwise loss function taking into account the order in the ranking of gallery images with respect to different probe images.

A Multi-loss Deep Network Based on Pyramid Pooling for Person Re-identification

A multi-loss siamese network with pyramid pooling structure for person re-ID that can get a better discriminative representation and achieve a better performance on two large public datasets including Market1501 and CUHK03.

A divide-and-unite deep network for person re-identification

A novel architecture of discriminative descriptor learning is proposed, which is based on the global feature and supplemented by part features, and which can achieve remarkable performance against numerous state-of-the-arts benchmarks.

An Improved Deep Mutual-Attention Learning Model for Person Re-Identification

A novel attention-based Siamese network driven by a mutual-attention module decomposed into spatial and channel components that is thoroughly evaluated on extensively used large-scale datasets, Market-1501 and Duke-MTMC-ReID.

Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends

A systematic challenge-specific literature survey of 230+ papers between the years of 2015-21 is presented where the person re-Id approaches are reviewed in such solution-oriented perspective and several diversified prominent developing trends in the respective research domain are presented.

Learning View-Specific Deep Networks for Person Re-Identification

A deep neural network-based framework which utilizes the view information in the feature extraction stage and proposes an iterative algorithm to optimize the parameters of the view-specific networks from coarse to fine to better adapt the re-id problem.

Enforcing Affinity Feature Learning through Self-attention for Person Re-identification

Extensive experiments on three large-scale datasets show that network architectures augmented with the proposed self-attention module systematically improve their accuracy and outperform various state-of-the-art models by a large margin.



Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function

A novel multi-channel parts-based convolutional neural network model under the triplet framework for person re-identification that significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based ones, on the challenging i-LIDS, VIPeR, PRID2011 and CUHK01 datasets.

DeepReID: Deep Filter Pairing Neural Network for Person Re-identification

A novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter is proposed and significantly outperforms state-of-the-art methods on this dataset.

Embedding Deep Metric for Person Re-identification: A Study Against Large Variations

A novel moderate positive sample mining method to train robust CNN for person re-identification, dealing with the problem of large variation is proposed and the learning by a metric weight constraint is improved, so that the learned metric has a better generalization ability.

Person Re-identification by Multi-hypergraph Fusion

This paper proposes to effectively leverage multiple off-the-shelf features via multi-hypergraph fusion and achieves superior performance as compared with the most recent state-of- the-arts.

PersonNet: Person Re-identification with Deep Convolutional Neural Networks

A deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification and an adaptive Root- Mean-Square (RMSProp) gradient decent algorithm is integrated into this architecture, which is beneficial to deep nets.

Video-Based Person Re-Identification With Accumulative Motion Context

The experimental results demonstrate that the proposed AMOC network outperforms state-of-the-arts for video-based re-identification significantly and confirm the advantage of exploiting long-range motion context forVideo-based person re-Identification, validating the motivation evidently.

Towards Open-World Person Re-Identification by One-Shot Group-Based Verification

A novel transfer local relative distance comparison model is formulated to address the open-world person re-identification problem by one-shot group-based verification and outperforms both non-transfer learning and existing transfer learning based re-id methods.

Temporal Model Adaptation for Person Re-identification

This work introduces a similarity-dissimilarity learning method which can be trained in an incremental fashion by means of a stochastic alternating directions methods of multipliers optimization procedure and exploits a graph-based approach to present the user only the most informative probe-gallery matches that should be used to update the model.

Person Re-identification by Efficient Impostor-Based Metric Learning

This paper addresses the first problem by learning the transition from one camera to the other by learning a Mahalanobis metric using pairs of labeled samples from different cameras, which additionally provides much better generalization properties.

Scalable Person Re-identification: A Benchmark

A minor contribution, inspired by recent advances in large-scale image search, an unsupervised Bag-of-Words descriptor is proposed that yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large- scale 500k dataset.