VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
Sihan Chen, Handong Li, Jing Liu, Mingzhen Sun, Qunbo Wang, Zijia Zhao, Xinxin Zhu
Topics & Concepts
Foundation (evidence)Computer scienceEngineeringWork (physics)Field (mathematics)Measure (data warehouse)Feature (linguistics)Artificial intelligenceIdentification (biology)Context (archaeology)Multimodal Machine Learning ApplicationsVideo Analysis and SummarizationAuthorship Attribution and Profiling