Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization

Zhou, Yang; Yu, Kai; Leng, Biao; Zhang, Zhang; Li, Dangwei; Huang, Kaiqi

doi:10.5244/c.31.69

Cited by 30 publications

(27 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to verify the performance of the proposed method on the PETA and RAP datasets, we compared it with the two traditional pedestrian attribute recognition representative methods; ikSVM [2,17] and ELF [18], and another four deep learning-based methods, including ACN [5], DeepMAR [19], WPAL [8] and multi-task CNN [6].…”

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

confidence: 99%

See 1 more Smart Citation

Pedestrian Attributes Recognition in Surveillance Scenarios Using Multi-Task Lightweight Convolutional Neural Network

Yan

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Pedestrian attributes (such as gender, age, hairstyle, and clothing) can effectively represent the appearance of pedestrians. These are high-level semantic features that are robust to illumination, deformation, etc. Therefore, they can be widely used in person re-identification, video structuring analysis and other applications. In this paper, a pedestrian attributes recognition method for surveillance scenarios using a multi-task lightweight convolutional neural network is proposed. Firstly, the labels of the attributes for each pedestrian image are integrated into a label vector. Then, a multi-task lightweight Convolutional Neural Network (CNN) is designed, which consists of five convolutional layers, three pooling layers and two fully connected layers to extract the deep features of pedestrian images. Considering that the data distribution of the datasets is unbalanced, the loss function is improved based on the sigmoid cross-entropy, and the scale factor is added to balance the amount of various attributes data. Through training the network, the mapping relationship model between the deep features of pedestrian images and the integration label vector of their attributes is established, which can be used to predict each attribute of the pedestrian. The experiments were conducted on two public pedestrian attributes datasets in surveillance scenarios, namely PETA and RAP. The results show that, compared with the state-of-the-art pedestrian attributes recognition methods, the proposed method can achieve a superior accuracy by 91.88% on PETA and 87.44% on RAP respectively.

show abstract

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

confidence: 99%

“…In contrast to previous methods of attributes recognition using the whole pedestrian image, WPAL [8] first determines the location of different attributes by the weakly supervised method, obtaining the attribute detection result, and then predicts the attributes in the detected results.…”

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

confidence: 99%

Pedestrian Attributes Recognition in Surveillance Scenarios Using Multi-Task Lightweight Convolutional Neural Network

Yan

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The contribution of each attribute determines the weight of the corresponding CNN. Zhou et al [21] first extracted mid-level features from detection layers using GoogLeNet. They localized the pedestrian attributes by fusing and clustering the activation maps of the detection layers.…”

Section: Related Workmentioning

confidence: 99%

Depthwise Separable Convolutional Neural Networks for Pedestrian Attribute Recognition

Junejo

Ahmed

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

Video surveillance is ubiquitous. In addition to understanding various scene objects, extracting human visual attributes from the scene has attracted tremendous traction over the past many years. This is a challenging problem even for human observers. This is a multi-label problem, i.e., a subject in a scene can have multiple attributes that we are hoping to recognize, such as shoes types, clothing type, wearing some accessory, or carrying some object or not, etc. Solutions have been presented over the years and many researchers have employed convolutional neural networks (CNNs). In this work, we propose using Depthwise Separable Convolution Neural Network (DS-CNN) to solve the pedestrian attribute recognition problem. The network employs depthwise separable convolution layers (DSCL), instead of the regular 2D convolution layers. DS-CNN performs extremely well, especially with smaller datasets. In addition, with a compact network, DS-CNN reduces the number of trainable parameters while making learning efficient. We evaluated our method on two benchmark pedestrian datasets and results show improvements over the state of the art.

show abstract

“…Dividing the human body part into 15 parts, [14] train a separate CNN for each part where the weight of a CNN is based on the contribution of a particular attribute. [15] makes use of the GoogLeNet to extract mid-level features from detection layers. Activation maps of these detected layers are fused, and clustering is performed to localize pedestrian attributes.…”

Section: Related Workmentioning

confidence: 99%

A multi-branch separable convolution neural network for pedestrian attribute recognition

Junejo

Ahmed

2020

Heliyon

View full text Add to dashboard Cite

Video surveillance applications have made great strides in making the world a safer place. Extracting visual attributes from a scene, such as the type of shoes, the type of clothing, carrying any object or not, or wearing any accessory etc., is a challenging problem and an efficient solution holds the key to a great number of applications. In this paper, we present a multi-branch convolutional neural network that uses depthwise separable convolution (DSC) layers to solve the pedestrian attribute recognition problem. Researchers have proposed various solutions over the years making use of convolutional neural networks (CNN), however, we introduce DSC layers to the CNN for the problem of pedestrian attribute recognition. In addition, we make a novel use of the different color spaces and create a 3-branch CNN, denoted as 3bCNN, that is efficient, especially with smaller datasets. We experiment on two benchmark datasets and show results with improvement over the state of the art.

show abstract

Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization

Cited by 30 publications

References 13 publications

Pedestrian Attributes Recognition in Surveillance Scenarios Using Multi-Task Lightweight Convolutional Neural Network

Pedestrian Attributes Recognition in Surveillance Scenarios Using Multi-Task Lightweight Convolutional Neural Network

Depthwise Separable Convolutional Neural Networks for Pedestrian Attribute Recognition

A multi-branch separable convolution neural network for pedestrian attribute recognition

Contact Info

Product

Resources

About