InternVideo
Public【ECCV 2024】用于多模态理解的视频基础模型与数据
action-recognitionbenchmarkcontrastive-learningfoundation-modelsinstruction-tuningmasked-autoencodermultimodalopen-set-recognitionself-supervisedspatio-temporal-action-localization
创建时间:2022-11-23T20:57:00
更新时间:2025-12-08T03:18:42
2.1K
Stars
7
Stars Increase