| Paper ID | IVMSP-17.2 |
| Paper Title |
STABLE AND EFFECTIVE ONE-STEP METHOD FOR PERSON SEARCH |
| Authors |
Ning Lv, Xuezhi Xiang, Xinyao Wang, Jie Yang, Rokia Abdeen, Harbin Engineering University, China; Abdulmotaleb El Saddik, University of Ottawa, Canada |
| Session | IVMSP-17: Looking at People |
| Location | Gather.Town |
| Session Time: | Wednesday, 09 June, 16:30 - 17:15 |
| Presentation Time: | Wednesday, 09 June, 16:30 - 17:15 |
| Presentation |
Poster
|
| Topic |
Image, Video, and Multidimensional Signal Processing: [IVSMR] Image & Video Sensing, Modeling, and Representation |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Person search, which requires both pedestrian detection and person re-identification, is a challenging computer vision task applied to real-world scenarios. The challenges faced by detection and re-identification, such as occlusion, poor illumination, confusing background, are still urgent for person search. In addition, one-step methods for person search need to deal with the divergence between two tasks. In this work, we propose an end-to-end model containing the feature extractor, the region proposal network and the multi-task learning module. In order to process divergence between detection and re-identification, we introduce switchable normalization and gradient centralization to improve the stability of the model. To solve the imbalance problem of hard examples, we introduce focal loss as a classification loss in the multi-task learning module. The experimental results on two benchmarks, i.e., CUHK-SYSU and PRW, well demonstrate that our method outperforms the state-of-the-art one-step methods. |
