Crossmark

Enhancing multi-level cross-modal interaction with false negative-aware contrastive learning for text-video retrieval

Published Online: 2025-09-05

Published Print: 2025-09

Authors

Kim, Eungyeop https://orcid.org/0009-0007-7271-5119
Lee, Changhee https://orcid.org/0000-0002-8681-4739
Funding

Funding for this research was provided by:

Department of Artificial Intelligence, Korea University (RS-2019-II190079, RS-2019-II190079)
License Information

Text and Data Mining valid from 2025-09-01

Version of Record valid from 2025-09-01
More Information

Article History

Accepted: 29 July 2025

First Online: 5 September 2025

Document is current