Localization Guided Learning for Pedestrian Attribute Recognition
arXiv:1808.09102
Abstract
Pedestrian attribute recognition has attracted many attentions due to its wide applications in scene understanding and person analysis from surveillance videos. Existing methods try to use additional pose, part or viewpoint information to complement the global feature representation for attribute classification. However, these methods face difficulties in localizing the areas corresponding to different attributes. To address this problem, we propose a novel Localization Guided Network which assigns attribute-specific weights to local features based on the affinity between proposals pre-extracted proposals and attribute locations. The advantage of our model is that our local features are learned automatically for each attribute and emphasized by the interaction with global features. We demonstrate the effectiveness of our Localization Guided Network on two pedestrian attribute benchmarks (PA-100K and RAP). Our result surpasses the previous state-of-the-art in all five metrics on both datasets.
arXiv commentAccepted by BMVC 2018
Cited by in corpus (9)
- Dynamic Curriculum Learning for Imbalanced Data Classification
- Pedestrian Attribute Recognition: A Survey
- Sequence-based Person Attribute Recognition with Joint CTC-Attention Model
- Cerberus: Attribute-based person re-identification using semantic IDs
- Hierarchical Feature Embedding for Attribute Recognition
- Data Augmentation Imbalance For Imbalanced Attribute Classification
- Distraction-Aware Feature Learning for Human Attribute Recognition via Coarse-to-Fine Attention Mechanism
- Robust Pedestrian Attribute Recognition Using Group Sparsity for Occlusion Videos
- Identity-Aware Attribute Recognition via Real-Time Distributed Inference in Mobile Edge Clouds