Attribute Recognition by Joint Recurrent Learning of Context and Correlation

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.

Accepted by ICCV 2017

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Neural Machine Translation by Jointly Learning to Align and Translate
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Show and Tell: A Neural Image Caption Generator
• Contextual Action Recognition with R*CNN
• Semantic Regularisation for Recurrent Image Annotation
• Multi-Task Curriculum Transfer Deep Learning of Clothing Attributes

Cited by in corpus (11)

• Visual Affordance and Function Understanding: A Survey
• Dynamic Curriculum Learning for Imbalanced Data Classification
• Pedestrian Attribute Recognition: A Survey
• Pose-Normalized Image Generation for Person Re-identification
• CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
• Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
• Adapting RNN Sequence Prediction Model to Multi-label Set Prediction
• Attribute Aware Pooling for Pedestrian Attribute Recognition
• Sequence-based Person Attribute Recognition with Joint CTC-Attention Model
• Class Rectification Hard Mining for Imbalanced Deep Learning
• Implicit Context-aware Learning and Discovery for Streaming Data Analytics