Pose-Driven Deep Convolutional Model for Person Re-identification

Su, Chi; Li, Jianing; Zhang, Shiliang; Xing, Junliang; Gao, Wen; Tian, Qi

doi:10.1109/iccv.2017.427

Cited by 777 publications

(522 citation statements)

References 63 publications

(177 reference statements)

Supporting

Mentioning

522

Contrasting

Order By: Relevance

“…By minimizing L, the proposed approach learns the foreground feature representations and the background feature representations simultaneously. Unlike existing works [1], [2], [3], [5], [7], [6], the prediction of the background and the training of person reidentification model are not separate. The addition of the target enhancement module and target attention loss makes the two branches couple and promote each other, which allows our model to obtain a more accurate separation of the foreground and background.…”

Section: The Overall Training Objectivementioning

confidence: 96%

“…To alleviate the adverse influence from the backgrounds, numerous methods [1], [2], [3], [4], [5], [6], [7], [8], [9] have been proposed. In [1], [2], [3], human landmark detectors are used to extract human keypoints and generate human part bounding boxes. In [5], [7], [6], segmentation models on pedestrian are applied to generate the whole body masks or multiple semantic regions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Líu¹,

Feng²,

Qi³

et al. 2017

IEEE Trans. on Image Process.

547

317

View full text Add to dashboard Cite

Abstract-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 approaches extract discriminative features from the whole frame at one glimpse without differentiating various parts of the persons to identify. It is essentially important to examine multiple highly discriminative local regions of the person images in details through multiple glimpses for dealing with the large appearance variance.In this paper, we propose 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. The end-to-end CAN learns to selectively focus on parts of pairs of person images after taking a few glimpses of them and adaptively comparing their appearance. The CAN model is able to learn which parts of images are relevant for discerning persons and automatically integrates information from different parts to determine whether a pair of images belongs to the same person. In other words, our proposed CAN model simulates the human perception process to verify whether two images are from the same person. Extensive experiments on four benchmark person re-identification datasets, including CUHK01, CHUHK03, Market-1501 and VIPeR, clearly demonstrate that our proposed end-to-end CAN for person re-identification outperforms well established baselines significantly and offer new state-of-the-art performance.

show abstract

Section: The Overall Training Objectivementioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

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

Líu¹,

Feng²,

Qi³

et al. 2017

IEEE Trans. on Image Process.

547

317

View full text Add to dashboard Cite

show abstract

“…Many solutions have used additional semantic cues such as human pose or body parts to further improve the classification performance. Su et al [20] proposed a Pose-driven Deep Convolutional (PDC) model to learn improved feature extraction and matching models from end-to-end. Wei et al [24] also adopted the human pose estimation, or key point detection approach, in his Global-Local-Alignment Descriptor (GLAD) algorithm.…”

Section: Aam Heatmapmentioning

confidence: 99%

AANet: Attribute Attention Network for Person Re-Identifications

Tay

Roy

Yap

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

314

155

View full text Add to dashboard Cite

This paper proposes Attribute Attention Network (AANet), a new architecture that integrates person attributes and attribute attention maps into a classification framework to solve the person re-identification (re-ID) problem. Many person re-ID models typically employ semantic cues such as body parts or human pose to improve the re-ID performance. Attribute information, however, is often not utilized. The proposed AANet leverages on a baseline model that uses body parts and integrates the key attribute information in an unified learning framework. The AANet consists of a global person ID task, a part detection task and a crucial attribute detection task. By estimating the class responses of individual attributes and combining them to form the attribute attention map (AAM), a very strong discriminatory representation is constructed. The proposed AANet outperforms the best state-of-the-art method [22] using ResNet-50 by 3.36% in mAP and 3.12% in Rank-1 accuracy on DukeMTMC-reID dataset. On Market1501 dataset, AANet achieves 92.38% mAP and 95.10% Rank-1 accuracy with re-ranking, outperforming [13], another state of the art method using ResNet-152, by 1.42% in mAP and 0.47% in Rank-1 accuracy. In addition, AANet can perform person attribute prediction (e.g., gender, hair length, clothing length etc.), and localize the attributes in the query image.

show abstract

“…Person Re-ID. Person Re-ID in still images is widely explored [22]- [32]. Currently, the researchers start to focus on video-based person Re-ID [2], [33].…”

Section: Related Workmentioning

confidence: 99%

Few-Shot Deep Adversarial Learning for Video-Based Person Re-Identification

Wang

Yin

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Recent years have witnessed a great development of deep learning based video person re-identification (Re-ID).A key factor for video person Re-ID is how to effectively construct discriminative video feature representations for the robustness to many complicated situations like occlusions. Recent part-based approaches employ spatial and temporal attention to extract the representative local features. While the correlations between the parts are ignored in the previous methods, to leverage the relations of different parts, we propose an innovative adaptive graph representation learning scheme for video person Re-ID, which enables the contextual interactions between the relevant regional features. Specifically, we exploit pose alignment connection and feature affinity connection to construct an adaptive structure-aware adjacency graph, which models the intrinsic relations between graph nodes. We perform feature propagation on the adjacency graph to refine the original regional features iteratively, the neighbor nodes information is taken into account for part feature representation. To learn the compact and discriminative representations, we further propose a novel temporal resolution-aware regularization, which enforces the consistency among different temporal resolutions for the same identities. We conduct extensive evaluations on four benchmarks, i.e. iLIDS-VID, PRID2011, MARS, and DukeMTMC-VideoReID, the experimental results achieve the competitive performance which demonstrates the effectiveness of our proposed method.

show abstract

Pose-Driven Deep Convolutional Model for Person Re-identification

Cited by 777 publications

References 63 publications

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

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

AANet: Attribute Attention Network for Person Re-Identifications

Few-Shot Deep Adversarial Learning for Video-Based Person Re-Identification

Contact Info

Product

Resources

About