Correction: BoostTrack: boosting the similarity measure and detection confidence for improved multiple object tracking
Hyper-parameters I oU , Mh D and shape are tuned to work with the original implementation and corrected implementation results in slightly worse results.We provide the corrected versions of Tables 1, 2 and 3 from the paper.Note that even the results of the settings that do not depend on S shape are slightly different from the original paper due to the different Python package versions.
Authors
- Branimir Todorović (ORCID: https://orcid.org/0000-0002-1792-1311)
- Vukasin D. Stanojevic (ORCID: https://orcid.org/0000-0002-5439-1057)
Institutions
- University of Nis (RS)
Publication Details
- Journal
- Machine Vision and Applications
- Published
- 2024-08-31
- DOI
- https://doi.org/10.1007/s00138-024-01605-4
- Citations
- 2
- Primary Topic
- Video Surveillance and Tracking Methods
- Type
- article
- Field-Weighted Citation Impact
- 0.50