HyperAIHyperAI超神経
ホームニュース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
HyperAIHyperAI超神経

Video Question Answering On Msrvtt Qa

評価指標

Accuracy

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
Accuracy
Paper TitleRepository
FrozenBiLM47.0Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
mPLUG-248.0mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
FrozenBiLM (0-shot)16.7Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
VIOLETv244.5An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling
Singularity-temporal43.9Revealing Single Frame Bias for Video-and-Language Learning
HBI46.2Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
VALOR49.2VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
Singularity43.5Revealing Single Frame Bias for Video-and-Language Learning
VAST50.1VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
Mirasol3B50.42Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities-
VindLU44.6VindLU: A Recipe for Effective Video-and-Language Pretraining
COSA49.2COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
MA-LMM48.5MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
EMCL-Net45.8Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
0 of 14 row(s) selected.