HyperAIHyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAIHyperAI초신경

Video Retrieval On Vatex

평가 지표

text-to-video R@1
text-to-video R@10
text-to-video R@5

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
text-to-video R@1
text-to-video R@10
text-to-video R@5
Paper TitleRepository
VAST83.099.298.2VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
QB-Norm+CLIP2Video58.893.8-Cross Modal Retrieval with Querybank Normalisation
CLIP2Video57.390-CLIP2Video: Mastering Video-Text Retrieval via Image CLIP
Side4Video68.897.093.5Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning
VALOR78.598.797.1VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
Cap4Video66.697.093.1Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?
InternVideo2-6B75.5--InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
GRAM87.7100-Gramian Multimodal Representation Learning and Alignment
TS2-Net59.195.2-TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval
LAFF59.191.7-Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval
Unmasked Teacher7297.895.1Unmasked Teacher: Towards Training-Efficient Video Foundation Models
InternVideo71.1--InternVideo: General Video Foundation Models via Generative and Discriminative Learning
TeachCLIP63.696.191.9Holistic Features are almost Sufficient for Text-to-Video Retrieval
0 of 13 row(s) selected.