Human detection aims at finding the location of Humans in digital images and videos. Human detection is an essential and significant task in automotive safety, robotics, image retrieval, and intelligent video surveillance system.
Our works focus on three aspects, deep model, contextual information and transfer learning.
Highlights
Single-Pedestrian Detection aided by Multi-pedestrian Detection
W. Ouyang and X. Wang.
In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2013.
PDF Project Page
Modeling Mutual Visibility Relationship with a Deep Model in Pedestrian Detection
W. Ouyang, X. Zeng and X. Wang
In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2013
PDF Project Page
A Discriminative Deep Model for Pedestrian Detection with Occlusion Handling
W. Ouyang and X. Wang
In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2012
PDF Project Page
Transferring a Generic Pedestrian Detector Towards Specific Scenes
M. Wang, W. Li and X. Wang
In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2012
PDF Project Page
Automatic Adaptation of a Generic Pedestrian Detector to a Specific Traffic Scene
M. Wang and X. Wang
In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2011
PDF Project Page