HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Zero Shot Video Retrieval On Activitynet

評価指標

text-to-video R@1
video-to-text R@1

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
text-to-video R@1
video-to-text R@1
Paper TitleRepository
InternVideo30.731.4InternVideo: General Video Foundation Models via Generative and Discriminative Learning
VideoCoCa34.533.0VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners-
vid-TLDR (UMT-L)42.841.2vid-TLDR: Training Free Token merging for Light-weight Video Transformer
GRAM59.050.9Gramian Multimodal Representation Learning and Alignment
InternVideo2-1B60.454.8InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
LanguageBind(ViT-L/14)38.435.7LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
UMT-L (ViT-L/16)42.840.7Unmasked Teacher: Towards Training-Efficient Video Foundation Models
Singularity-temporal-17M30.6-Revealing Single Frame Bias for Video-and-Language Learning
LanguageBind(ViT-H/14)41.039.1LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
InternVideo2-6B63.256.5InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
BT-Adapter37.0-BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning
Singularity-temporal-5M30.8-Revealing Single Frame Bias for Video-and-Language Learning
0 of 12 row(s) selected.