In this work, we propose a novel Spatial-Temporal Attention (STA) approach to tackle the large-scale person reidentification task in videos. Different from the most existing methods …
Person search has recently gained attention as the novel task of finding a person, provided as a cropped sample, from a gallery of non-cropped images, whereby several other people …
C Han, J Ye, Y Zhong, X Tan… - Proceedings of the …, 2019 - openaccess.thecvf.com
Person search aims at localizing and identifying a query person from a gallery of uncropped scene images. Different from person re-identification (re-ID), its performance also depends …
The task of reidentifying groups of people under different camera views is an important yet less-studied problem. Group reidentification (Re-ID) is a very challenging task since it is not …
AS Nassar, S Lefèvre… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
We propose to jointly learn multi-view geometry and warping between views of the same object instances for robust cross-view object detection. What makes multi-view object …
W Song, S Li, T Chang, A Hao… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Despite growing progresses in recent years, cross-scenario person re-identification remains challenging, mainly due to the pedestrians commonly surrounded by highly-complex …
J Ge, G Gao, Z Liu - arXiv preprint arXiv:1912.03083, 2019 - arxiv.org
Searching persons in large-scale image databases with the query of natural language description is a more practical important applications in video surveillance. Intuitively, for …
Y Zhang, X Li, Z Zhang - IEEE Transactions on Cybernetics, 2019 - ieeexplore.ieee.org
The person search problem aims to find the target person in the scene images, which presents high demands for both effectiveness and efficiency. In this paper, we present a …
We introduce knowledge distillation for end-to-end person search. End-to-End methods are the current state-of-the-art for person search that solve both detection and re-identification …