A Relative Positional Embedding Scheme for Transformer-Based Person Re-Identification 


Vol. 48,  No. 9, pp. 1175-1178, Sep.  2023
10.7840/kics.2023.48.9.1175


PDF
  Abstract

In this letter, we propose a training scheme for a transformer-based person re-identification model using relative positional embeddings. To overcome the limitations of existing methods that rely on the visual information of an image, we define the topological and positional characteristics of a person's body structure through relative positional embeddings and uses them as an additional cue. In a set of experiment conducted for five popular person ReID benchmark datasets, the proposed scheme brings promising improvement.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

S. Kim and G. Kim, "A Relative Positional Embedding Scheme for Transformer-Based Person Re-Identification," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 9, pp. 1175-1178, 2023. DOI: 10.7840/kics.2023.48.9.1175.

[ACM Style]

Seong-Su Kim and Gyeonghwan Kim. 2023. A Relative Positional Embedding Scheme for Transformer-Based Person Re-Identification. The Journal of Korean Institute of Communications and Information Sciences, 48, 9, (2023), 1175-1178. DOI: 10.7840/kics.2023.48.9.1175.

[KICS Style]

Seong-Su Kim and Gyeonghwan Kim, "A Relative Positional Embedding Scheme for Transformer-Based Person Re-Identification," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 9, pp. 1175-1178, 9. 2023. (https://doi.org/10.7840/kics.2023.48.9.1175)
Vol. 48, No. 9 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880