Back to Search
Start Over
Improving Person Re-Identification With Iterative Impression Aggregation.
- Source :
-
IEEE Transactions on Image Processing . 2020, Vol. 29, p9559-9571. 13p. - Publication Year :
- 2020
-
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. [ABSTRACT FROM AUTHOR]
- Subjects :
- *PERFORMANCE standards
*TASK analysis
*INTUITION
*IDENTIFICATION
Subjects
Details
- Language :
- English
- ISSN :
- 10577149
- Volume :
- 29
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Image Processing
- Publication Type :
- Academic Journal
- Accession number :
- 170078651
- Full Text :
- https://doi.org/10.1109/TIP.2020.3029415