Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/CLIP4Clip

CLIP4Clip

Reported on 77 benchmarks across 5 tasks · 1 paper · 53 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision76 results

VideoonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2021-04-18
81.6
best: 90.8 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSR-VTT-1kA
video-to-text R@1· uses extra data· 2021-04-18
42.7
best: 64.8 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSR-VTT-1kA
video-to-text R@10· uses extra data· 2021-04-18
80.6
best: 91.1 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSR-VTT-1kA
video-to-text R@5· uses extra data· 2021-04-18
70.9
best: 783 (PIDRo)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonActivityNet
text-to-video R@1· 2021-04-18
40.5
best: 74.1 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonActivityNet
text-to-video R@5· 2021-04-18
73.4
best: 90.9 (VAST)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonActivityNet
text-to-video R@50· 2021-04-18
98.2
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonDiDeMo
text-to-video R@1· uses extra data· 2021-04-18
43.4
best: 74.2 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonDiDeMo
text-to-video R@10· uses extra data· 2021-04-18
80.6
best: 94.2 (vid-TLDR (UMT-L))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonDiDeMo
text-to-video R@5· uses extra data· 2021-04-18
70.2
best: 91.2 (vid-TLDR (UMT-L))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonLSMDC
text-to-video R@1· uses extra data· 2021-04-18
21.6
best: 46.4 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonLSMDC
text-to-video R@10· uses extra data· 2021-04-18
49.8
best: 92.8 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonLSMDC
text-to-video R@5· uses extra data· 2021-04-18
41.8
best: 80.1 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSVD
text-to-video R@1· uses extra data· 2021-04-18
46.2
best: 61.4 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSVD
text-to-video R@10· uses extra data· 2021-04-18
84.6
best: 90.3 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSVD
text-to-video R@5· uses extra data· 2021-04-18
76.1
best: 87.6 (CAMoE)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSVD
video-to-text R@1· uses extra data· 2021-04-18
62
best: 85.2 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSVD
video-to-text R@10· uses extra data· 2021-04-18
92.6
best: 97.1 (PAU)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSVD
video-to-text R@5· uses extra data· 2021-04-18
87.3
best: 94.5 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2021-04-18
81.6
best: 90.8 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSR-VTT-1kA
video-to-text R@1· uses extra data· 2021-04-18
42.7
best: 64.8 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSR-VTT-1kA
video-to-text R@10· uses extra data· 2021-04-18
80.6
best: 91.1 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSR-VTT-1kA
video-to-text R@5· uses extra data· 2021-04-18
70.9
best: 783 (PIDRo)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonActivityNet
text-to-video R@1· 2021-04-18
40.5
best: 74.1 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonActivityNet
text-to-video R@5· 2021-04-18
73.4
best: 90.9 (VAST)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonActivityNet
text-to-video R@50· 2021-04-18
98.2
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2021-04-18
43.4
best: 74.2 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonDiDeMo
text-to-video R@10· uses extra data· 2021-04-18
80.6
best: 94.2 (vid-TLDR (UMT-L))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonDiDeMo
text-to-video R@5· uses extra data· 2021-04-18
70.2
best: 91.2 (vid-TLDR (UMT-L))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonLSMDC
text-to-video R@1· uses extra data· 2021-04-18
21.6
best: 46.4 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonLSMDC
text-to-video R@10· uses extra data· 2021-04-18
49.8
best: 92.8 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonLSMDC
text-to-video R@5· uses extra data· 2021-04-18
41.8
best: 80.1 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSVD
text-to-video R@1· uses extra data· 2021-04-18
46.2
best: 61.4 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSVD
text-to-video R@10· uses extra data· 2021-04-18
84.6
best: 90.3 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSVD
text-to-video R@5· uses extra data· 2021-04-18
76.1
best: 87.6 (CAMoE)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSVD
video-to-text R@1· uses extra data· 2021-04-18
62
best: 85.2 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSVD
video-to-text R@10· uses extra data· 2021-04-18
92.6
best: 97.1 (PAU)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSVD
video-to-text R@5· uses extra data· 2021-04-18
87.3
best: 94.5 (HunYuan_tvr (huge))
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Text to Video RetrievalonMSR-VTT
text-to-video R@1· 2021-04-18
44.5
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@1· 2021-04-18
32
best: 55.9 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@10· 2021-04-18
66.9
best: 85.1 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@5· 2021-04-18
57
best: 78.3 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonMSVD
text-to-video Mean Rank· 2021-04-18
17.8
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonMSVD
text-to-video Median Rank· 2021-04-18
2
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonMSVD
text-to-video R@1· 2021-04-18
38.5
best: 59.3 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonMSVD
text-to-video R@10· 2021-04-18
76.8
best: 89.6 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonMSVD
text-to-video R@5· 2021-04-18
66.9
best: 84.4 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonLSMDC
text-to-video Mean Rank· uses extra data· 2021-04-18
117
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonLSMDC
text-to-video Median Rank· uses extra data· 2021-04-18
28
best: 50.7 (MILES)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonLSMDC
text-to-video R@1· uses extra data· 2021-04-18
15.1
best: 33.8 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonLSMDC
text-to-video R@10· uses extra data· 2021-04-18
36.4
best: 62.2 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonLSMDC
text-to-video R@5· uses extra data· 2021-04-18
28.5
best: 55.9 (InternVideo2-6B)
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSR-VTT-1kA
text-to-video Mean Rank· uses extra data· 2021-04-18
15.3
best: 28.2 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSR-VTT-1kA
text-to-video Median Rank· uses extra data· 2021-04-18
2
best: 13 (JSFusion)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSR-VTT-1kA
video-to-text Median Rank· uses extra data· 2021-04-18
2
best: 5 (CLIP)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonActivityNet
text-to-video Mean Rank· 2021-04-18
7.5
best: 23.1 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonActivityNet
text-to-video Median Rank· 2021-04-18
2
best: 6 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonDiDeMo
text-to-video Mean Rank· uses extra data· 2021-04-18
17.5
best: 43.7 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonDiDeMo
text-to-video Median Rank· uses extra data· 2021-04-18
2
best: 8.3 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonLSMDC
text-to-video Mean Rank· uses extra data· 2021-04-18
58
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSVD
text-to-video Mean Rank· uses extra data· 2021-04-18
10
best: 23.1 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSVD
text-to-video Median Rank· uses extra data· 2021-04-18
2
best: 6 (SSML)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
VideoonMSVD
video-to-text Median Rank· uses extra data· 2021-04-18
1
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSR-VTT-1kA
text-to-video Mean Rank· uses extra data· 2021-04-18
15.3
best: 28.2 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSR-VTT-1kA
text-to-video Median Rank· uses extra data· 2021-04-18
2
best: 13 (JSFusion)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSR-VTT-1kA
video-to-text Median Rank· uses extra data· 2021-04-18
2
best: 5 (CLIP)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonActivityNet
text-to-video Mean Rank· 2021-04-18
7.5
best: 23.1 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonActivityNet
text-to-video Median Rank· 2021-04-18
2
best: 6 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonDiDeMo
text-to-video Mean Rank· uses extra data· 2021-04-18
17.5
best: 43.7 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonDiDeMo
text-to-video Median Rank· uses extra data· 2021-04-18
2
best: 8.3 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonLSMDC
text-to-video Mean Rank· uses extra data· 2021-04-18
58
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSVD
text-to-video Mean Rank· uses extra data· 2021-04-18
10
best: 23.1 (Collaborative Experts)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSVD
text-to-video Median Rank· uses extra data· 2021-04-18
2
best: 6 (SSML)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Video RetrievalonMSVD
video-to-text Median Rank· uses extra data· 2021-04-18
1
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonMSR-VTT
text-to-video Mean Rank· 2021-04-18
34
best: 148.1 (MMT)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860
Zero-Shot Video RetrievalonMSR-VTT
text-to-video Median Rank· 2021-04-18
4
best: 66 (MMT)
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860

Audio1 result

10-shot image generationonMSR-VTT
text-to-video R@1· 2021-04-18
44.5
SOTA
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval arXiv:2104.08860