[EMNLP2024 Demo], [ICASSP 2025], [ICASSP 2026] A user-friendly library for reproducible video moment retrieval and highlight detection. It also supports audio moment retrieval.
audio natural-language-processing video computer-vision video-processing audio-processing multimodal video-moment-retrieval moment-retrieval highlight-detection audio-moment-retrieval
-
Updated
Mar 26, 2026 - Python