Video Retrieval on VATEX

27개 결과 · ⬇ CSV · JSON

text-to-video R@1

Rank	Model	text-to-video R@1	text-to-video R@5	text-to-video R@10	text-to-video R@50	text-to-video MedianR	text-to-video MeanR	video-to-text R@1	video-to-text R@10	Extra Training Data	Paper	Code	Year
1	Vote-in-Context 자동 추출	99.6	–	–	–	–	–	–	–		Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers		2025
2	GRAM	87.7	–	100	–	–	–	84.6	100	✓	Gramian Multimodal Representation Learning and Alignment	ispamm/GRAM · luigisigillo/gwit	2024
3	VAST	83.0	98.2	99.2	–	–	–	–	–	✓	VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset	TXH-mercury/VALOR · txh-mercury/vast	2023
4	VALOR	78.5	97.1	98.7	–	–	–	–	–	✓	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset	TXH-mercury/VALOR	2023
5	InternVideo2-6B	75.5	–	–	–	–	–	89.3	–	✓	InternVideo2: Scaling Foundation Models for Multimodal Video Understanding	opengvlab/internvideo · opengvlab/internvideo2	2024
6	Unmasked Teacher	72	95.1	97.8	–	–	–	86.0	99.6		Unmasked Teacher: Towards Training-Efficient Video Foundation Models	opengvlab/unmasked_teacher	2023
7	InternVideo	71.1	–	–	–	–	–	87.2	–		InternVideo: General Video Foundation Models via Generative and Discriminative Learning	opengvlab/internvideo · yingsen1/unimd	2022
8	Side4Video	68.8	93.5	97.0	1.0	2.7	–	–	–		Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning	whwu95/ATM · HJYao00/Side4Video	2023
9	Cap4Video	66.6	93.1	97.0	–	1	2.7	80.9	99.6		Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?	whwu95/Cap4Video · whwu95/text4vis · whwu95/GPT4Vis · +1	2022
10	TeachCLIP	63.6	91.9	96.1	–	–	–	–	–		Holistic Features are almost Sufficient for Text-to-Video Retrieval	ruc-aimc-lab/teachclip	2024
11	TS2-Net	59.1	–	95.2	–	–	–	–	–		TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval	yuqi657/ts2_net	2022
11	LAFF	59.1	–	91.7	96.3	–	–	–	–		Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval	ruc-aimc-lab/laff	2021
13	QB-Norm+CLIP2Video	58.8	–	93.8	–	–	–	–	–	✓	Cross Modal Retrieval with Querybank Normalisation	ioanacroi/qb-norm	2021
14	CLIP2Video	57.3	–	90	95.5	–	–	–	–	✓	CLIP2Video: Mastering Video-Text Retrieval via Image CLIP	CryhanFang/CLIP2Video	2021
15	GRAM	87.7	–	100	–	–	–	84.6	100	✓	Gramian Multimodal Representation Learning and Alignment	ispamm/GRAM · luigisigillo/gwit	2024
16	VAST	83.0	98.2	99.2	–	–	–	–	–	✓	VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset	TXH-mercury/VALOR · txh-mercury/vast	2023
17	VALOR	78.5	97.1	98.7	–	–	–	–	–	✓	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset	TXH-mercury/VALOR	2023
18	InternVideo2-6B	75.5	–	–	–	–	–	89.3	–	✓	InternVideo2: Scaling Foundation Models for Multimodal Video Understanding	opengvlab/internvideo · opengvlab/internvideo2	2024
19	Unmasked Teacher	72	95.1	97.8	–	–	–	86.0	99.6		Unmasked Teacher: Towards Training-Efficient Video Foundation Models	opengvlab/unmasked_teacher	2023
20	InternVideo	71.1	–	–	–	–	–	87.2	–		InternVideo: General Video Foundation Models via Generative and Discriminative Learning	opengvlab/internvideo · yingsen1/unimd	2022