Name
Title | ||
|---|---|---|
Revisiting k-Reciprocal Distance Re-Ranking for Skeleton-Based Person Re-Identification |
Abstract | ||
|---|---|---|
Person re-identification (re-ID) as a retrieval task often utilizes a re-ranking model to improve performance. Existing re-ranking methods are typically designed for conventional person re-ID with RGB images, while skeleton representation re-ranking for skeleton-based person re-ID still remains to be explored. To fill this gap, we revisit the k -reciprocal distance re-ranking model in this letter, and propose a generic re-ranking method that exploits the salient skeleton features to perform k -reciprocal distance encoding for skeleton-based person re-ID re-ranking. In particular, we devise the skeleton sequence pooling to aggregate the most salient features of skeletons within a sequence, and combine both original Euclidean distance and k -reciprocal distance to re-rank the skeleton sequence representations for person re-ID. Furthermore, we propose the context-based Rank-1 voting that jointly exploits the initial ranking list and re-ranking list to vote for the top candidate to enhance the Rank-1 matching. Extensive experiments on three public benchmarks demonstrate that our approach can effectively re-rank different state-of-the-art skeleton representations and significantly improve their person re-ID performance. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/LSP.2022.3212634 | IEEE SIGNAL PROCESSING LETTERS |
Keywords | DocType | Volume |
Skeleton-based person re-identification, reranking, k-reciprocal distance, skeleton sequence pooling. | Journal | 29 |
ISSN | Citations | PageRank |
1070-9908 | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Haocong Rao | 1 | 0 | 0.34 |
| Yuan Li | 2 | 0 | 0.34 |
| Chunyan Miao | 3 | 2307 | 195.72 |