Attention-Based Pedestrian Attribute Analysis

Tan, Zichang; Yang, Yang; Wan, Jun; Hang, Hanyuan; Guo, Guodong; Li, Stan Z.

doi:10.1109/tip.2019.2919199

Cited by 84 publications

(49 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With a view to select the discriminative regions of the input data, [38] proposes a model considering three aspects: 1) Using the parsing technique [87], they split features of each body-part and help the model learns the location-oriented features by pixel-to-pixel supervision. 2) Multiple attention maps are assigned to each label due to empowering the features from the relevant regions to that label and suppressing the other features.…”

Section: Attention Based Methodsmentioning

confidence: 99%

“…Table 1 shows the performance of the HAR approaches over the last decade and indicates a consistent improvement of methods over time. In 2016, the performance evaluation of [29] on the RAP and PETA datasets achieved to F1 score 66.12 and 84.90, respectively, while these number were improved to 79.98 and 86.87 in the year 2019 [38]. Furthermore, according to Table 1, it is clear that challenges of attributes localization and attributes correlation have attracted the most attention over the recent years, which indicates that extracting distinctive fine-grained features from relevant locations of the given input images is the most important aspect of HAR models.…”

Section: Category-based Performance Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

Human Attribute Recognition: A Comprehensive Survey

Yaghoubi¹,

Khezeli²,

Borza³

et al. 2020

Preprint

View full text Add to dashboard Cite

Over the last decade, the field of Human Attribute Recognition (HAR) has dramatically changed, mainly due to the improvements brought by deep learning solutions. This survey reviews the progress obtained in HAR, considering the transition from the traditional hand-crafted to deep-learning approaches. The most relevant works on the field are analyzed concerning the advances proposed to address the HAR's typical challenges. Furthermore, we outline the applications and typical evaluation metrics used in the HAR context. Finally, we provide a comprehensive review of the publicly available datasets for the development and evaluation of novel HAR approaches.

show abstract

Section: Attention Based Methodsmentioning

confidence: 99%

Section: Category-based Performance Comparisonmentioning

confidence: 99%

Human Attribute Recognition: A Comprehensive Survey

Yaghoubi¹,

Khezeli²,

Borza³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Attention mechanism, first proposed in [20] for enhanced contextual information extraction in natural language processing, has been adopted in numerous fields including medical image processing [21], [22]. This mechanism assists faster convergence with considerable performance improvement by eliminating the redundant parts while putting more attention on the region-of-interests through the generalization of the predominant contextual information.…”

Section: A Proposed Tri-level Attention Schemementioning

confidence: 99%

CovTANet: A Hybrid Tri-Level Attention-Based Network for Lesion Segmentation, Diagnosis, and Severity Prediction of COVID-19 Chest CT Scans

Mahmud

Alam

Chowdhury

et al. 2021

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Rapid and precise diagnosis of COVID-19 is one of the major challenges faced by the global community to control the spread of this overgrowing pandemic. In this paper, a hybrid neural network is proposed, named CovTANet, to provide an end-to-end clinical diagnostic tool for early diagnosis, lesion segmentation, and severity prediction of COVID-19 utilizing chest computer tomography (CT) scans. A multi-phase optimization strategy is introduced for solving the challenges of complicated diagnosis at a very early stage of infection, where an efficient lesion segmentation network is optimized initially which is later integrated into a joint optimization framework for the diagnosis and severity prediction tasks providing feature enhancement of the infected regions. Moreover, for overcoming the challenges with diffused, blurred, and varying shaped edges of COVID lesions with novel and diverse characteristics, a novel segmentation network is introduced, namely Tri-level Attention-based Segmentation Network (TA-SegNet). This network has significantly reduced semantic gaps in subsequent encoding decoding stages, with immense parallelization of multi-scale features for faster convergence providing considerable performance improvement over traditional networks. Furthermore, a novel tri-level attention mechanism has been introduced, which is repeatedly utilized over the network, combining channel, spatial, and pixel attention schemes for faster and efficient generalization of contextual information embedded in the feature map through feature recalibration and enhancement operations. Outstanding performances have been achieved in all three-tasks through extensive experimentation on a large publicly available dataset containing 1110 chest CT-volumes that signifies the effectiveness of the proposed scheme at the current stage of the pandemic.

show abstract

“…Due to the relationship between image features and attributes being not fully considered, the author not only investigated image feature and attribute feature together, but also developed a fusion attention mechanism as well as an improvement loss function to address the problem of imbalance attributes. Tan et al [18] proposed three attention mechanisms including parsing attention, label attention, and spatial attention to highlight regions or pixels against the variations, such as frequent pose variations, blur images, and camera angles. Specifically, parsing attention mainly focuses to extract image features, where label attention pays more attention to attribute features, and spatial attention aims at considering problems from a global perspective, however, they do not fully consider the correlation between attributes.…”

Section: Related Workmentioning

confidence: 99%

Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios

2019

View full text Add to dashboard Cite

Pedestrian attribute recognition is to predict a set of attribute labels of the pedestrian from surveillance scenarios, which is a very challenging task for computer vision due to poor image quality, continual appearance variations, as well as diverse spatial distribution of imbalanced attributes. It is desirable to model the label dependencies between different attributes to improve the recognition performance as each pedestrian normally possesses many attributes. In this paper, we treat pedestrian attribute recognition as multi-label classification and propose a novel model based on the graph convolutional network (GCN). The model is mainly divided into two parts, we first use convolutional neural network (CNN) to extract pedestrian feature, which is a normal operation processing image in deep learning, then we transfer attribute labels to word embedding and construct a correlation matrix between labels to help GCN propagate information between nodes. This paper applies the object classifiers learned by GCN to the image representation extracted by CNN to enable the model to have the ability to be end-to-end trainable. Experiments on pedestrian attribute recognition dataset show that the approach obviously outperforms other existing state-of-the-art methods.

show abstract

Attention-Based Pedestrian Attribute Analysis

Cited by 84 publications

References 50 publications

Human Attribute Recognition: A Comprehensive Survey

Human Attribute Recognition: A Comprehensive Survey

CovTANet: A Hybrid Tri-Level Attention-Based Network for Lesion Segmentation, Diagnosis, and Severity Prediction of COVID-19 Chest CT Scans

Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios

Contact Info

Product

Resources

About