READ: Reciprocal Attention Discriminator for Image-to-Video Re-Identification
Abstract
Person re-identification (re-ID) is the problem of visually identifying a person given a database of identities. In this work, we focus on image-to-video re-ID which compares a single query image to videos in the gallery. The main challenge is the asymmetry association of an image and a video, and overcoming the difference caused by the additional temporal dimension. To this end, we propose an attention-aware discriminator architecture. The attention occurs across different modalities, and even different identities to aggregate useful spatio-temporal information for comparison. The information is effectively fused into a united feature, followed by the final prediction of a similarity score. The performance of the method is shown with image-to-video person re-identification benchmarks (DukeMTMC-VideoReID, and MARS).
Cite
Text
Shim et al. "READ: Reciprocal Attention Discriminator for Image-to-Video Re-Identification." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58568-6_20Markdown
[Shim et al. "READ: Reciprocal Attention Discriminator for Image-to-Video Re-Identification." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/shim2020eccv-read/) doi:10.1007/978-3-030-58568-6_20BibTeX
@inproceedings{shim2020eccv-read,
title = {{READ: Reciprocal Attention Discriminator for Image-to-Video Re-Identification}},
author = {Shim, Minho and Ho, Hsuan-I and Kim, Jinhyung and Wee, Dongyoon},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2020},
doi = {10.1007/978-3-030-58568-6_20},
url = {https://mlanthology.org/eccv/2020/shim2020eccv-read/}
}