Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Chapter

Download BibTeX

Title

[FCM] Anchor generation crosscheck

Authors

[ 1 ] Instytut Telekomunikacji Multimedialnej, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ P ] employee

Scientific discipline (Law 2.0)

[2.3] Information and communication technology

Year of publication

2025

Chapter type

chapter in monograph / paper

Publication language

english

Abstract

PL Investigation of FCTM anchor discrepancies is a still ongoing activity. The anchor generation for FCTM-v2.0.0 (CPU) showed mismatch between results attained by various crosscheckers for HiEve dataset. This contribution confirms the same tendency with your results as compared to the others. The investigation for the source of discrepancies has been performed by running FCTM-v2.0.0 (CPU) for HiEve, TVD and SFU datasets over multiple hardware and software configurations. Additionally, the problem with negative MOTA score for HiEve sequences was observed. Additionally, the TVD-01 sequence had some problems to be fully evaluated on some configurations due to its length.

Pages (from - to)

1 - 3

Book

146 MPEG Meeting

Presented on

146 MPEG Meeting, 22-26.04.2024, Rennes, France

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.