Attribute Recognition by Joint Recurrent Learning of Context and Correlation
Open Access
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 531-540
Abstract
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. In this work, we formulate a Joint Recurrent Learning (JRL) model for exploring attribute context and correlation in order to improve attribute recognition given small sized training data with poor quality images. 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 network. We demonstrate the performance advantage and robustness of the JRL model over a wide range of state-of-the-art deep models for pedestrian attribute recognition, multi-label image classification, and multi-person image annotation on two largest pedestrian attribute benchmarks PETA and RAP.Keywords
All Related Versions
This publication has 35 references indexed in Scilit:
- Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Semantic Regularisation for Recurrent Image Annotation2017
- Joint Learning of Semantic and Latent Attributes2016
- Transferring a semantic representation for person re-identification and search2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Soft Biometrics; Human Identification Using Comparative DescriptionsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Classifier chains for multi-label classificationMachine Learning, 2011
- A New Baseline for Image Annotation2008
- A Set of Independent Necessary and Sufficient Conditions for Simple Majority DecisionEconometrica, 1952