← Zero-Shot Video Retrieval
Papers with Code · CC BY-SA 4.0

MSVD

아카이브 평가 14건 · 마지막 적재/변경

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델원본 지표·값논문구현
InternVideo2-6B
text-to-video R@1
59.3
video-to-text R@1
83.1
text-to-video R@5
84.4
text-to-video R@10
89.6
video-to-text R@5
94.2
video-to-text R@10
97.0
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
2024-03-22
코드 1 · 코드 2
InternVideo2-1B
text-to-video R@1
58.1
video-to-text R@1
83.3
text-to-video R@5
83.0
text-to-video R@10
88.4
video-to-text R@5
94.3
video-to-text R@10
96.9
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
2024-03-22
코드 1 · 코드 2
VAST, HowToCaption-finetuned
text-to-video R@1
54.8
text-to-video R@5
80.9
text-to-video R@10
87.2
text-to-video Median Rank
1
HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
2023-10-07
코드 1
LanguageBind(ViT-L/14)
text-to-video R@1
54.1
video-to-text R@1
69.7
text-to-video R@5
81.1
text-to-video R@10
88.1
video-to-text R@5
91.8
video-to-text R@10
97.9
text-to-video Median Rank
1.0
video-to-text Median Rank
1.0
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
2023-10-03
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
LanguageBind(ViT-H/14)
text-to-video R@1
53.9
video-to-text R@1
72.0
text-to-video R@5
80.4
text-to-video R@10
87.8
video-to-text R@5
91.4
video-to-text R@10
96.3
text-to-video Median Rank
1
video-to-text Median Rank
1
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
2023-10-03
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
vid-TLDR (UMT-L)
text-to-video R@1
50.0
video-to-text R@1
75.7
text-to-video R@5
77.6
text-to-video R@10
85.5
video-to-text R@5
90.0
video-to-text R@10
95.1
vid-TLDR: Training Free Token merging for Light-weight Video Transformer
2024-03-20
코드 1
UMT-L (ViT-L/16)
text-to-video R@1
49.0
video-to-text R@1
74.5
text-to-video R@5
76.9
text-to-video R@10
84.7
video-to-text R@5
89.7
video-to-text R@10
92.8
Unmasked Teacher: Towards Training-Efficient Video Foundation Models
2023-03-28
코드 1
HowToCaption
text-to-video R@1
44.5
text-to-video R@5
73.3
text-to-video R@10
82.1
text-to-video Median Rank
2
HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
2023-10-07
코드 1
MILES
text-to-video R@1
44.4
text-to-video R@5
76.2
text-to-video R@10
87.0
text-to-video Median Rank
2.0
MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval
2022-04-26
코드 1
Y. Ge et. al.
text-to-video R@1
43.6
text-to-video R@5
74.9
text-to-video R@10
84.9
text-to-video Median Rank
2.0
Bridging Video-text Retrieval with Multiple Choice Questions
2022-01-13
코드 1 · 코드 2
InternVideo
text-to-video R@1
43.4
video-to-text R@1
67.6
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
2022-12-06
코드 1 · 코드 2
CLIP4Clip
text-to-video R@1
38.5
text-to-video R@5
66.9
text-to-video R@10
76.8
text-to-video Median Rank
2
text-to-video Mean Rank
17.8
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
2021-04-18
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
LaT
text-to-video R@1
36.9
video-to-text R@1
34.4
text-to-video R@5
68.6
text-to-video R@10
81.0
video-to-text R@5
69.0
video-to-text R@10
79.2
text-to-video Median Rank
2
video-to-text Median Rank
3
LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval
2022-07-11
연결 없음
SSML
text-to-video R@1
13.66
text-to-video R@5
35.7
text-to-video R@10
47.74
Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning
2020-03-06
코드 1