Attention-Aware Compositional Network for Person Re-identification

@article{Xu2018AttentionAwareCN,
  title={Attention-Aware Compositional Network for Person Re-identification},
  author={Jing Xu and Rui Zhao and Feng Zhu and Huaming Wang and Wanli Ouyang},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={2119-2128}
}
  • J. Xu, Rui Zhao, Wanli Ouyang
  • Published 9 May 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Person re-identification (ReID) is to identify pedestrians observed from different camera views based on visual appearance. [] Key Method AACN consists of two main components: Pose-guided Part Attention (PPA) and Attention-aware Feature Composition (AFC). PPA is learned and applied to mask out undesirable background features in pedestrian feature maps. Furthermore, pose-guided visibility scores are estimated for body parts to deal with part occlusion in the proposed AFC module. Extensive experiments with…

Mask-Guided Region Attention Network for Person Re-Identification

TLDR
This paper presents a novel framework called Mask-Guided Region Attention Network (MGRAN) for person ReID, and evaluates the proposed method on three public datasets, including Market-1501, DukeMTMC-reID and CUHK03 to show the effectiveness of this method.

Quality-aware Part Models for Occluded Person Re-identification

TLDR
A novel method named Quality-aware Part Models (QPM) for occlusion-robust ReID, which does not rely on any outside tools in either the training or inference stages, and handles occlusions caused by both objects and other pedestrians; it is highly computationally efficient.

A part-based attention network for person re-identification

TLDR
This paper presents a part-based attention model consisting of a channel attention block and a spatial attention block to sequentially refine the convolutional descriptors of person body parts and demonstrates the effectiveness of the presented method.

Improve Person Re-Identification With Part Awareness Learning

TLDR
It is revealed that body part perception helps ReID model to capture a set of more diverse features from the body, with decreased similarity between part features and increased focus on different body regions.

A Hybrid of Hard and Soft Attention for Person Re-Identification

TLDR
A Hard$/$Soft hybrid Attention Network (HSAN) that combines pose information and attention mechanism to deal with the challenges of large human pose variations, viewpoint changes, severe occlusions and imprecise detection of persons.

Deep Attention Aware Feature Learning for Person Re-Identification

Parts Semantic Segmentation Aware Representation Learning for Person Re-Identification

TLDR
A person re-identification network which fuses global and local features, to deal with part misalignment problem, and a DropParts method to solve the parts missing problem, with which the local features are weighed according to the number of parts found by semantic segmentation.

Cross-Camera Person Re-Identification With Body-Guided Attention Network

TLDR
The proposed BANet aims to fully utilize fine-grained information of body region to guide the final process of feature extraction and validates the importance of attention mechanism in person ReID.
...

References

SHOWING 1-10 OF 62 REFERENCES

Pose-Invariant Embedding for Deep Person Re-Identification

TLDR
This paper introduces pose-invariant embedding (PIE) as a pedestrian descriptor and shows that PoseBox alone yields decent re-ID accuracy and that when integrated in the PBF network, the learned PIE descriptor produces competitive performance compared with state-of-the-art approaches.

Deeply-Learned Part-Aligned Representations for Person Re-identification

TLDR
This paper proposes a simple yet effective human part-aligned representation for handling the body part misalignment problem, and shows state-of-the-art results over standard datasets, Market-1501,CUHK03, CUHK01 and VIPeR.

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

TLDR
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.

Pedestrian Alignment Network for Large-scale Person Re-Identification

TLDR
This work introduces the pedestrian alignment network (PAN) which allows discriminative embedding learning pedestrian alignment without extra annotations, and observes that when the convolutional neural network learns to discriminate between different identities, the learned feature maps usually exhibit strong activations on the human body rather than the background.

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

TLDR
This paper proposes a new soft attention-based model, i.e., the end-to-end comparative attention network (CAN), specifically tailored for the task of person re-identification that outperforms well established baselines significantly and offers the new state-of-the-art performance.

Constrained Deep Metric Learning for Person Re-identification

TLDR
A novel CNN-based method to learn a discriminative metric with good robustness to the over-fitting problem in person re-identification is proposed and it is found that the selection of intra-class sample pairs is crucial for learning but has received little attention.

Transferring a semantic representation for person re-identification and search

TLDR
This paper presents a new semantic attribute learning approach for person re-identification and search that is trained on existing fashion photography datasets and adapted to provide a powerful semantic description of surveillance person detections, without requiring any surveillance domain supervision.

Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion

TLDR
This study proposes a novel Convolutional Neural Network, called Spindle Net, based on human body region guided multi-stage feature decomposition and tree-structured competitive feature fusion, which is the first time human body structure information is considered in a CNN framework to facilitate feature learning.

Joint Detection and Identification Feature Learning for Person Search

TLDR
A new deep learning framework for person search that jointly handles pedestrian detection and person re-identification in a single convolutional neural network and converges much faster and better than the conventional Softmax loss.

Scalable Person Re-identification: A Benchmark

TLDR
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.
...