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

Video Retrieval On Msvd

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
InternVideo2-6B61.485.2InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
InternVideo58.476.3InternVideo: General Video Foundation Models via Generative and Discriminative Learning
VLAB57.5-VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending-
CAMoE51.869.3Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss
DiffusionRet+QB-Norm47.960.3DiffusionRet: Generative Text-Video Retrieval with Diffusion Model
X-CLIP50.466.8X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval
MDMMT-256.8-MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization-
PAU47.368.9Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval
CLIP4Clip46.262.0CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
DiffusionRet46.661.9DiffusionRet: Generative Text-Video Retrieval with Diffusion Model
CLIP3759.9A Straightforward Framework For Video Retrieval Using CLIP
Cap4Video51.870.0Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?
HunYuan_tvr (huge)59.073.0Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations-
Collaborative Experts19.8-Use What You Have: Video Retrieval Using Representations From Collaborative Experts
vid-TLDR (UMT-L)57.982.7vid-TLDR: Training Free Token merging for Light-weight Video Transformer
LAFF45.4-Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval
QB-Norm+CLIP2Video48.0-Cross Modal Retrieval with Querybank Normalisation
X-Pool47.266.4X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval
CenterCLIP (ViT-B/16)50.668.4CenterCLIP: Token Clustering for Efficient Text-Video Retrieval
DMAE (ViT-B/32)48.7-Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning-
0 of 24 row(s) selected.