1. Towards Understanding and Inferring the Crowd: Guided Second Order Attention Networks and Re-identification for Multi-object Tracking
- Author
-
Li Jun, Niraj Bhujel, Yau Wei Yun, and Han Wang
- Subjects
business.industry ,Computer science ,SIGNAL (programming language) ,020206 networking & telecommunications ,02 engineering and technology ,Variation (game tree) ,Tracking (particle physics) ,Convolutional neural network ,Salient ,Video tracking ,0202 electrical engineering, electronic engineering, information engineering ,Clutter ,020201 artificial intelligence & image processing ,Computer vision ,Artificial intelligence ,business ,Feature learning - Abstract
Multi-human tracking in the crowded environment is a challenging problem due to occlusions, pose change, viewpoint variation and cluttered background. In this work, we propose a robust feature learning for tracking-by-detection methods based on second-order attention network that can capture higher-order relationships between salient features at the early stages of Convolutional Neural Network (CNN). Guided Second-Order Attention Network (GSAN) that, unlike the existing attention learning methods which are weakly-supervised, uses a supervisory signal based on the quality of the self-learned attention maps. More specifically, GSAN looks into the attended maps of a person having the highest confidence and supervise itself to look into the correct regions in the images of the person. Attention maps learned this way are spatially aligned and thus robust to camera-view changes and body pose variations. We verify the effectiveness of our approach by comparing with the state-of-the-art methods on challenging person re-identification and multi object tracking (MOT) datasets.
- Published
- 2020