@article{fu2020improving,
author = {Fu, Dengpan and Xin, Bo and Wang, Jingdong and Chen, Dongdong and Bao, Jianmin and Hua, Gang and Li, Houqiang},
title = {Improving Person Re-Identification With Iterative Impression Aggregation},
year = {2020},
month = {October},
abstract = {Our impression about one person often updates after we see more aspects of him/her and this process keeps iterating given more meetings. We formulate such an intuition into the problem of person re-identification (re-ID), where the representation of a query (probe) image is iteratively updated with new information from the candidates in the gallery. Specifically, we propose a simple attentional aggregation formulation to instantiate this idea and showcase that such a pipeline achieves competitive performance on standard benchmarks including CUHK03, Market-1501 and DukeMTMC. Not only does such a simple method improve the performance of the baseline models, it also achieves comparable performance with latest advanced re-ranking methods. Another advantage of this proposal is its flexibility to incorporate different representations and similarity metrics. By utilizing stronger representations and metrics, we further demonstrate state-of-the-art person re-ID performance, which also validates the general applicability of the proposed method.},
url = {http://approjects.co.za/?big=en-us/research/publication/improving-person-re-identification-with-iterative-impression-aggregation/},
pages = {9559-9571},
journal = {IEEE Transactions on Image Processing},
volume = {29},
}