Embedding-based pair generation for contrastive representation learning in audio-visual surveillance data

Wang, Wei-ChengWei-ChengWangDe Coninck, SanderSanderDe ConinckLeroux, SamSamLerouxSimoens, PieterPieterSimoens2025-02-042025-02-032025-02-0420252296-9144WOS:001406286400001https://imec-publications.be/handle/20.500.12860/45170Embedding-based pair generation for contrastive representation learning in audio-visual surveillance dataJournal article10.3389/frobt.2024.1490718WOS:001406286400001MEDLINE:39871999