MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model 文章
ArXiv CS.CV2026-05-26NEWSen作者: Eyal Hanania, Nadav Kirsch, Daniel Arkushin, Jonathan Benvenisti, Amos Bercovich, Elie Zemmour, Sahar Froim