Attribute Recognition by Joint Recurrent Learning of Context and Correlation

@article{Wang2017AttributeRB,
  title={Attribute Recognition by Joint Recurrent Learning of Context and Correlation},
  author={Jingya Wang and Xiatian Zhu and Shaogang Gong and Wei Li},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={531-540}
}
  • Jingya Wang, Xiatian Zhu, Wei Li
  • Published 25 September 2017
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
Recognising semantic pedestrian attributes in surveillance images is a challenging task for computer vision, particularly when the imaging quality is poor with complex background clutter and uncontrolled viewing conditions, and the number of labelled training data is small. [] Key Method The JRL model learns jointly pedestrian attribute correlations in a pedestrian image and in particular their sequential ordering dependencies (latent high-order correlation) in an end-to-end encoder/ decoder recurrent…

Figures and Tables from this paper

Joint Learning of Dictionary and Convolutional Network for Pedestrian Attribute Recognition
TLDR
To learn multiple attributes jointly, the attributes are modeled as a sub space and a dictionary is introduced to represent the subspace and a novel learning algorithm is proposed to optimize the dictionary and the convolutional network corporately.
Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios
TLDR
The object classifiers learned by GCN is applied to the image representation extracted by CNN to enable the model to have the ability to be end-to-end trainable and outperforms other existing state-of-the-art methods.
Pedestrian Attribute Recognition via Hierarchical Multi-task Learning and Relationship Attention
TLDR
A novel end-to-end hierarchical deep learning approach to pedestrian Attribute Recognition is proposed and very competitive results are reached on the RAP and PETA databases, indicating the effectiveness and superiority of the proposed approach.
Recurrent Attention Model for Pedestrian Attribute Recognition
TLDR
This paper proposes end-to-end Recurrent Convolutional (RC) and Recurrent Attention (RA) models, which are complementary to each other and achieves state-of-the-art results, based on pedestrian attribute datasets, i.e. standard PETA and RAP datasets.
Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition
TLDR
A unified framework, named CAScaded Split-and-Aggregate Learning with Feature Recombination (CAS-SAL-FR), to learn the above modules jointly and concurrently achieves new state-of-the-art performance.
Pedestrian Attribute Recognition by Joint Visual-semantic Reasoning and Knowledge Distillation
TLDR
A graph-based global reasoning framework to jointly model potential visualsemantic relations of attributes and distill auxiliary human parsing knowledge from a pre-trained teacher model to guide the relational learning.
Reinforced Sample Re-weighting for Pedestrian Attribute Recognition
  • Yuan Liu
  • Computer Science
    2020 International Joint Conference on Neural Networks (IJCNN)
  • 2020
TLDR
Reinforced Sample Re-weighting (RSR) is proposed, a novel approach to re-weight samples in a batch during back-propagation through reinforcement learning that achieves state-of-the-art performance against other existing methods on three large scale pedestrian attribute datasets.
An Evaluation Of Design Choices For Pedestrian Attribute Recognition In Video
TLDR
This work investigates the applicability of several recent strategies to include temporal information into the recognition process, identifies the most promising building blocks and creates a strong baseline model, which achieves state-of-the-art attribute recognition accuracy in videos and provides a good basis for future research.
Visual-Semantic Graph Reasoning for Pedestrian Attribute Recognition
TLDR
A novel visual-semantic graph reasoning framework to address pedestrian attribute recognition in surveillance and shows superiority of the proposed method over state-of-the-art methods and effectiveness of the joint GCN structures for sequential attribute prediction.
...
...

References

SHOWING 1-10 OF 54 REFERENCES
Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios
TLDR
Two deep learning based models to recognize pedestrian attributes are proposed and the gender of woman can contribute to the representation oflong hair and wearing skirt, and the deep learning framework which recognizes multiple attributes jointly (DeepMAR) is proposed.
Person Attribute Recognition with a Jointly-Trained Holistic CNN Model
TLDR
This paper proposes a method to jointly train a CNN model for all attributes that can take advantage of possible dependencies between them, considering as input only the image without additional external pose, part or context information.
A Richly Annotated Dataset for Pedestrian Attribute Recognition
TLDR
A Richly Annotated Pedestrian (RAP) dataset from real multi-camera surveillance scenarios with long term collection, where data samples are annotated with not only fine-grained human attributes but also environmental and contextual factors.
Learning to Recognize Pedestrian Attribute
TLDR
This study presents an alternative approach that exploits the context of neighboring pedestrian images for improved attribute inference compared to the conventional SVM-based method and conducts extensive experiments to evaluate the informativeness of background and foreground features for attribute recognition.
Deep Attributes Driven Multi-Camera Person Re-identification
TLDR
By directly using the deep attributes with simple Cosine distance, this work has obtained surprisingly good accuracy on four person ReID datasets, and shows that a simple metric learning modular further boosts the method, making it significantly outperform many recent works.
Multi-task Curriculum Transfer Deep Learning of Clothing Attributes
TLDR
A novel Multi-Task Curriculum Transfer (MTCT) deep learning method to explore multiple sources of different types of web annotations with multi-labelled fine-grained attributes for model transfer learning from well-controlled shop clothing images collected from web retailers to in-the-wild images from the street.
Sequential Person Recognition in Photo Albums with a Recurrent Network
TLDR
This work proposes a novel recurrent network architecture, in which relational information between instances labels and appearance are modeled jointly, and demonstrates that this simple but elegant formulation achieves state-of-the-art performance on the newly released People In Photo Albums (PIPA) dataset.
Human Attribute Recognition by Deep Hierarchical Contexts
TLDR
This work trains a Convolutional Neural Network to select the most attribute-descriptive human parts from all poselet detections, and combines them with the whole body as a pose-normalized deep representation, which surpasses competitive baselines on this dataset and other popular ones.
Pedestrian Attribute Classification in Surveillance: Database and Evaluation
TLDR
This paper constructs an Attributed Pedestrians in Surveillance (APiS) database with various scenes, and develops an evaluation protocol for researchers to evaluate pedestrian attribute classification algorithms.
CNN-RNN: A Unified Framework for Multi-label Image Classification
TLDR
The proposed CNN-RNN framework learns a joint image-label embedding to characterize the semantic label dependency as well as the image- label relevance, and it can be trained end-to-end from scratch to integrate both information in a unified framework.
...
...