Joint instance and feature importance re-weighting for person reidentification

Q Zhou, S Zheng, H Yang, Y Wang… - 2016 IEEE International …, 2016 - ieeexplore.ieee.org
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016ieeexplore.ieee.org
Person reidentification refers to the task of recognizing the same person under different non-
overlapping camera views. Presently, person reidentification based on metric learning is
proved to be effective among various techniques, which exploits the labeled data to learn a
subspace that maximizes the inter-person divergence while minimizes the intra-person
divergence. However, these methods fail to take the different impacts of various instances
and local features into account. To address this issue, we propose to learn a projection …
Person reidentification refers to the task of recognizing the same person under different non-overlapping camera views. Presently, person reidentification based on metric learning is proved to be effective among various techniques, which exploits the labeled data to learn a subspace that maximizes the inter-person divergence while minimizes the intra-person divergence. However, these methods fail to take the different impacts of various instances and local features into account. To address this issue, we propose to learn a projection matrix such that the importance of different instances and local features are re-weighted jointly. We also come up with a simplified formulation of the proposed algorithm, thus it can be solved by the efficient UDFS optimization algorithm. Extensive experiments on the VIPeR and iLIDS datasets demonstrate the effectiveness and efficiency of our algorithm.
ieeexplore.ieee.org
Showing the best result for this search. See all results