Pose Guided Deep Model for Pedestrian Attribute Recognition in Surveillance Scenarios

Li, Dangwei; Chen, Xiaotang; Zhang, Zhang; Huang, Kaiqi

doi:10.1109/icme.2018.8486604

Cited by 122 publications

(92 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(3) Attention-based methods including HP-Net [20] and DIAA [19] relying on multi-scale attention mechanism, and VeSPA [25] which perform view-specific attribute prediction through a coarse view predictor. (4) Part-based methods including recently proposed PGDM [15] and LG-Net [19], which relying on external pose estimation or region proposal module. Table 3 and Table 4 show the comparison results on three different datasets.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…Zhu et al [40] divide the whole image into 15 rigid patches and fuse features from different patches. Yang et al [34] and Li et al [15] leverage external pose estimation module to localize body-parts. Liu et al [19] also explore attribute regions in a weakly supervised manner while they assign attribute regions to some fixed proposals generated by EdgeBoxes [42] in advance, which is not fully-adaptive and end-to-end trainable.…”

Section: Related Workmentioning

confidence: 99%

“…An alternative way is to leverage predefined rigid parts [40] or external part localization modules [15,19,34,35]. Some works apply body-parts detection [35], pose estimation [15,34] and region proposals [19] to learn part-based local features. As shown in Figure 1 (d), these methods extract local features from the localized body parts (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization

Tang

Sheng

Zhang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

111

109

View full text Add to dashboard Cite

Pedestrian attribute recognition has been an emerging research topic in the area of video surveillance. To predict the existence of a particular attribute, it is demanded to localize the regions related to the attribute. However, in this task, the region annotations are not available. How to carve out these attribute-related regions remains challenging. Existing methods applied attribute-agnostic visual attention or heuristic body-part localization mechanisms to enhance the local feature representations, while neglecting to employ attributes to define local feature areas. We propose a flexible Attribute Localization Module (ALM) to adaptively discover the most discriminative regions and learns the regional features for each attribute at multiple levels. Moreover, a feature pyramid architecture is also introduced to enhance the attribute-specific localization at low-levels with high-level semantic guidance. The proposed framework does not require additional region annotations and can be trained end-to-end with multi-level deep supervision. Extensive experiments show that the proposed method achieves state-of-the-art results on three pedestrian attribute datasets, including PETA, RAP, and PA-100K.

show abstract

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization

Tang

Sheng

Zhang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

111

109

View full text Add to dashboard Cite

show abstract

“…Deep learning based methodologies are widely used for semantic description based person retrieval due to its efficient learning. Convolutional Neural Network (CNN) based algorithms are reported for person attribute recognition [10][11][12] as well as for person retrieval [5,[13][14][15][16]. Semantic Retrieval Convolution Neural Network (SRCNN) [10] retrieves the soft biometrics with recognition rate of 20.1% and 46.4% at rank-1 for one-shot and multi-shot identification respectively on SoBiR [8] dataset.…”

Section: Introductionmentioning

confidence: 99%

“…Semantic Retrieval Convolution Neural Network (SRCNN) [10] retrieves the soft biometrics with recognition rate of 20.1% and 46.4% at rank-1 for one-shot and multi-shot identification respectively on SoBiR [8] dataset. Li et al [12] explore the spatial correlations of person attributes with human body structure e.g., hair and glasses are most correlated with the head. They propose Pose Guided Deep Model (PGDM) consisting of coarse pose estimation, body part localization, and fusion of body part features.…”

Section: Introductionmentioning

confidence: 99%

Visual appearance based person retrieval in unconstrained environment videos

Galiyawala

Raval

Dave

2019

Image and Vision Computing

View full text Add to dashboard Cite

Visual appearance-based person retrieval is a challenging problem in surveillance. It uses attributes like height, cloth color, cloth type and gender to describe a human. Such attributes are known as soft biometrics. This paper proposes person retrieval from surveillance video using height, torso cloth type, torso cloth color and gender. The approach introduces an adaptive torso patch extraction and bounding box regression to improve the retrieval. The algorithm uses fine-tuned Mask R-CNN and DenseNet-169 for person detection and attribute classification respectively. The performance is analyzed on AVSS 2018 challenge II dataset and it achieves 11.35% improvement over state-of-the-art based on average Intersection over Union measure.

show abstract

Graph-Boosted Attentive Network for Semantic Body Parsing

Wang

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Human body parsing remains a challenging problem in natural scenes due to multi-instance and inter-part semantic confusions as well as occlusions. This paper proposes a novel approach to decomposing multiple human bodies into semantic part regions in unconstrained environments. Specifically we propose a convolutional neural network (CNN) architecture which comprises of novel semantic and contour attention mechanisms across feature hierarchy to resolve the semantic ambiguities and boundary localization issues related to semantic body parsing. We further propose to encode estimated pose as higher-level contextual information which is combined with local semantic cues in a novel graphical model in a principled manner. In this proposed model, the lower-level semantic cues can be recursively updated by propagating higher-level contextual information from estimated pose and vice versa across the graph, so as to alleviate erroneous pose information and pixel level predictions. We further propose an optimization technique to efficiently derive the solutions. Our proposed method achieves the state-of-art results on the challenging Pascal Person-Part dataset.

show abstract

Pose Guided Deep Model for Pedestrian Attribute Recognition in Surveillance Scenarios

Cited by 122 publications

References 16 publications

Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization

Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization

Visual appearance based person retrieval in unconstrained environment videos

Graph-Boosted Attentive Network for Semantic Body Parsing

Contact Info

Product

Resources

About