Robust Pedestrian Attribute Recognition Using Group Sparsity for Occlusion Videos
This work addresses occlusion handling for pedestrian attribute recognition in videos, which is an incremental improvement over existing methods.
The paper tackled occlusion in pedestrian attribute recognition from videos by proposing a group sparsity-based temporal attention method to handle correlated attributes, achieving higher F1-scores than state-of-the-art methods on two datasets.
Occlusion processing is a key issue in pedestrian attribute recognition (PAR). Nevertheless, several existing video-based PAR methods have not yet considered occlusion handling in depth. In this paper, we formulate finding non-occluded frames as sparsity-based temporal attention of a crowded video. In this manner, a model is guided not to pay attention to the occluded frame. However, temporal sparsity cannot include a correlation between attributes when occlusion occurs. For example, "boots" and "shoe color" cannot be recognized when the foot is invisible. To solve the uncorrelated attention issue, we also propose a novel group sparsity-based temporal attention module. Group sparsity is applied across attention weights in correlated attributes. Thus, attention weights in a group are forced to pay attention to the same frames. Experimental results showed that the proposed method achieved a higher F1-score than the state-of-the-art methods on two video-based PAR datasets.