HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis

Liu, Xihui; Zhao, Haiyu; Tian, Maoqing; Sheng, Lu; Shao, Jing; Yi, Shuai; Yan, Junjie; Wang, Xiaogang

doi:10.1109/iccv.2017.46

Cited by 491 publications

(416 citation statements)

References 37 publications

Supporting

Mentioning

414

Contrasting

Order By: Relevance

“…prediction order, attribute group, which are hard to determine in real applications. (2) Attention-based: Some researchers [20,24,25,38] introduce the visual attention mechanism in attribute recognition. Liu et al [20] propose a multi-directional attention model to learn multi-scale attentive features for pedestrian analysis.…”

Section: Related Workmentioning

confidence: 99%

“…(2) Attention-based: Some researchers [20,24,25,38] introduce the visual attention mechanism in attribute recognition. Liu et al [20] propose a multi-directional attention model to learn multi-scale attentive features for pedestrian analysis. Sarafianos et al [24] extend the spatial regularization module [38] to learn effective attention maps at multiple scales.…”

Section: Related Workmentioning

confidence: 99%

“…Only 51 binary attributes with the positive ratio higher than 1% are selected for evaluation. (3) The PA-100K dataset [20] is to-date the largest dataset for pedestrian attribute recognition, which contains 100,000 pedestrian images in total collected from outdoor surveillance cameras. Each image is annotated with 26 commonly used attributes.…”

Section: Datasets and Evaluation Metricsmentioning

confidence: 99%

“…Recent methods attempt to leverage the attention localization to promote learning discriminative features for attribute recognition. A popular solution [20,24,38] is to employ the visual attention mechanism to capture the most relevant features. These methods usually generate attention masks from certain layers and then multiply them to corresponded feature maps so as to extract the attentive features.…”

Section: Introductionmentioning

confidence: 99%

See 3 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)

Self Cite

119

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: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Datasets and Evaluation Metricsmentioning

confidence: 99%

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)

Self Cite

119

109

View full text Add to dashboard Cite

show abstract

“…Attributes for ReID. Semantic attributes [46,25,7] have been exploited as feature representations for person reidentification tasks. Previous work [47,6,20,42,58] leverages the attribute labels provided by original dataset to generate attribute-aware feature representation.…”

Section: Related Workmentioning

confidence: 99%

Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification

Guo

Yuan

Huang

et al. 2019

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

199

View full text Add to dashboard Cite

Person re-identification is a challenging task due to various complex factors. Recent studies have attempted to integrate human parsing results or externally defined attributes to help capture human parts or important object regions. On the other hand, there still exist many useful contextual cues that do not fall into the scope of predefined human parts or attributes. In this paper, we address the missed contextual cues by exploiting both the accurate human parts and the coarse non-human parts. In our implementation, we apply a human parsing model to extract the binary human part masks and a self-attention mechanism to capture the soft latent (non-human) part masks. We verify the effectiveness of our approach with new state-of-the-art performances on three challenging benchmarks: Market-1501, DukeMTMC-reID and CUHK03. Our implementation is available at https://github.com/ggjy/P2Net.pytorch.

show abstract

Topology and channel affinity reinforced global attention for person re‐identification

Wang

Gao

Xin

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Person re‐identification (re‐id), with the goal to recognize persons from images captured by nonoverlapping cameras, is a challenging topic in computer vision. It has been studied extensively in recent years, and the attention mechanism is widely applied in person re‐id. But many works mainly focus on extracting discriminative features from local saliency regions, while ignoring some potentially global information between whole‐body features and body‐part features. In this study, we first proposed two effective global information for extracting discriminative features: spatial topology information (STI) and channel affinity information (CAI). On this basis, we further propose a Multi‐information Fusion reinforced Global Attention (MIFGA) module which can effectively fuse a variety of information and utilize more comprehensive information to guide the learning of attention, so as to obtain pedestrian features that are conducive to clustering. Specifically, the proposed MIFGA module includes spatial attention (MIFGA‐S) and channel attention (MIFGA‐C). MIFGA‐S mainly utilizes local feature semantic information and STI to guide the learning of spatial attention. Furthermore, to mine the potential topology information in original feature maps, the self‐learning graph convolution network is proposed. MIFGA‐C fuses channel semantic information and CAI to guide the learning of channel attention. Extensive ablation studies demonstrate that our proposed MIFGA significantly enhances the baseline model and achieves a competitive performance compared with the state‐of‐the‐art person re‐id methods on standard data sets Market‐1501, DukeMTMC‐reID, and CUHK03.

show abstract

HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis

Cited by 491 publications

References 37 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

Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification

Topology and channel affinity reinforced global attention for person re‐identification

Contact Info

Product

Resources

About