Attributes-aided part detection and refinement for person re-identification

Li, Shuzhao; Yu, Huimin; Hu, Rong

doi:10.1016/j.patcog.2019.107016

Cited by 59 publications

(16 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…APR [9] proposed a multitask learning framework to learn visual representation and attribute representation separately. APDR [29] detected the attribute relevant parts with attribute detection network and extracted the feature of image patch where pedestrian exists. AANET [11] proposed a "soft" attention module to focus on the pedestrian-involved region.…”

Section: B Attribute Auxiliary Person Re-idmentioning

confidence: 99%

Graph Neural Network Based Attribute Auxiliary Structured Grouping for Person Re-Identification

Tang

Gao²,

Chen

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Recently, person re-identification (re-ID) with weakly labeled or unlabeled data has drawn much attention in open-set and cross-domain re-ID systems especially for the attribute auxiliary weakly supervised person re-ID. Although state-of-the-art clustering-based methods have achieved good performance, the pseudo labels generated through clustering are often low-quality and noisy. To address this problem, we propose a graph neural network based Attribute Auxiliary structured Grouping (A 2 G) to improve the confidence of the pseudo labels. Different from the existing clustering-based approaches that only utilize the similarity in feature space, we learn the feature representation from the similarities in both attribute space and feature space by graph learning on the pedestrian attribute graph. Specifically, we first utilize the pair-wise attribute similarity to represent the relation between two pedestrians to construct a pedestrian attribute graph. Furthermore, we aggregate the features from their neighborhood on a pedestrian attribute graph by the graph neural network, which would make the attribute similar pairs closer and simultaneously take the dissimilar pairs further in the feature space. Finally, to avoid the over-confidence of the hard pseudo labels, we regularize the learning of the embedding model with the smoothed pseudo label (SPL) in the optimization of the feature embedding network. We conduct extensive experiments on several person re-ID datasets to validate the efficacy of our proposed method. The results demonstrate that our technique is effective and promising for person re-ID tasks.INDEX TERMS Unsupervised person re-identification, attribute-auxiliary structured grouping, graph neural network.

show abstract

Section: B Attribute Auxiliary Person Re-idmentioning

confidence: 99%

Graph Neural Network Based Attribute Auxiliary Structured Grouping for Person Re-Identification

Tang

Gao²,

Chen

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The AANet [39] combined the global representation with three tasks, including person ReID, body part localization, and person attribute recognition. The APDR [19] method fused attribute features and body part features to result in the final local features which are then concatenated with the global features for person re-identification.…”

Section: Related Workmentioning

confidence: 99%

“…We compare our method (GPS) to the recent state-of-the-art that used body parts: MGCAM [37], SPReID [16], P 2 -Net [10]. For attribute-based approach, we compare our results with ACRN [35], MLFN [1], A 3 M [11], AANet [39], APR [21], AFFNet [25], PAAN [52], and APDR [19]. Among them, AANet [39], PAAN [52], and APDR [19] are works that use both attributes and body parts to enhance the performance of person ReID task.…”

Section: Comparison To the State Of The Artmentioning

confidence: 99%

“…For attribute-based approach, we compare our results with ACRN [35], MLFN [1], A 3 M [11], AANet [39], APR [21], AFFNet [25], PAAN [52], and APDR [19]. Among them, AANet [39], PAAN [52], and APDR [19] are works that use both attributes and body parts to enhance the performance of person ReID task. However, there is no work that leverage the relationship between attributes and body parts to extract person signature embedding as our proposed method.…”

Section: Comparison To the State Of The Artmentioning

confidence: 99%

“…With the rise of deep learning, most of the recent studies utilize Convolutional Neural Network (CNN) to tackle the person ReID problem. Many approaches have been proposed such as metric learning [14,30,3], attention-based [40,47,2,27], GAN-based [32,9,57], attribute-based [19,21,11,1,25,52], and spatial-temporal-based methods [41].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Graph-based Person Signature for Person Re-Identifications

Nguyen¹,

Nguyen²,

Do³

et al. 2021

Preprint

View full text Add to dashboard Cite

The task of person re-identification (ReID) is to match images of the same person over multiple non-overlapping camera views. Due to the variations in visual factors, previous works have investigated how the person identity, body parts, and attributes benefit the person ReID problem. However, the correlations between attributes, body parts, and within each attribute are not fully utilized. In this paper, we propose a new method to effectively aggregate detailed person descriptions (attributes labels) and visual features (body parts and global features) into a graph, namely Graph-based Person Signature, and utilize Graph Convolutional Networks to learn the topological structure of the visual signature of a person. The graph is integrated into a multi-branch multi-task framework for person re-identification. The extensive experiments are conducted to demonstrate the effectiveness of our proposed approach on two large-scale datasets, including Market-1501 and DukeMTMC-ReID. Our approach achieves competitive results among the state of the art and outperforms other attribute-based or mask-guided methods. Source available at https://github.com/aioz-ai/CVPRW21_GPS.

show abstract