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/CenterCLIP (ViT-B/16)

CenterCLIP (ViT-B/16)

Reported on 80 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Computer Vision80 results

VideoonActivityNet
video-to-text Mean Rank· uses extra data· 2022-05-02
5.5
best: 6.7 (DiffusionRet+QB-Norm)
SOTA
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonActivityNet
video-to-text Median Rank· uses extra data· 2022-05-02
2
SOTA
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonActivityNet
video-to-text Mean Rank· uses extra data· 2022-05-02
5.5
best: 6.7 (DiffusionRet+QB-Norm)
SOTA
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonActivityNet
video-to-text Median Rank· uses extra data· 2022-05-02
2
SOTA
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSR-VTT-1kA
text-to-video Mean Rank· uses extra data· 2022-05-02
13.8
best: 28.2 (Collaborative Experts)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSR-VTT-1kA
text-to-video Median Rank· uses extra data· 2022-05-02
2
best: 13 (JSFusion)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2022-05-02
48.4
best: 62.9 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2022-05-02
82
best: 90.8 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSR-VTT-1kA
text-to-video R@5· uses extra data· 2022-05-02
73.8
best: 84.5 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSR-VTT-1kA
video-to-text Mean Rank· uses extra data· 2022-05-02
10.2
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSR-VTT-1kA
video-to-text Median Rank· uses extra data· 2022-05-02
2
best: 5 (CLIP)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSR-VTT-1kA
video-to-text R@1· uses extra data· 2022-05-02
47.7
best: 64.8 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSR-VTT-1kA
video-to-text R@10· uses extra data· 2022-05-02
83.3
best: 91.1 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSR-VTT-1kA
video-to-text R@5· uses extra data· 2022-05-02
75
best: 783 (PIDRo)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonActivityNet
text-to-video Mean Rank· uses extra data· 2022-05-02
5.7
best: 23.1 (Collaborative Experts)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonActivityNet
text-to-video Median Rank· uses extra data· 2022-05-02
2
best: 6 (Collaborative Experts)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonActivityNet
text-to-video R@1· uses extra data· 2022-05-02
46.2
best: 74.1 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonActivityNet
text-to-video R@10· uses extra data· 2022-05-02
87.6
best: 96.1 (GRAM)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonActivityNet
text-to-video R@5· uses extra data· 2022-05-02
77
best: 90.9 (VAST)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonActivityNet
video-to-text R@1· uses extra data· 2022-05-02
46.7
best: 69.7 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonActivityNet
video-to-text R@10· uses extra data· 2022-05-02
88
best: 95.4 (GRAM)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonActivityNet
video-to-text R@5· uses extra data· 2022-05-02
77.1
best: 89.1 (UMT-L (ViT-L/16))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonLSMDC
text-to-video Mean Rank· uses extra data· 2022-05-02
47.3
best: 58 (CLIP4Clip)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonLSMDC
text-to-video Median Rank· uses extra data· 2022-05-02
8
best: 56.5 (CLIP)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonLSMDC
text-to-video R@1· uses extra data· 2022-05-02
24.2
best: 46.4 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonLSMDC
text-to-video R@10· uses extra data· 2022-05-02
55.9
best: 92.8 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonLSMDC
text-to-video R@5· uses extra data· 2022-05-02
46.2
best: 80.1 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonLSMDC
video-to-text Mean Rank· uses extra data· 2022-05-02
41.3
best: 48.9 (HunYuan_tvr)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonLSMDC
video-to-text Median Rank· uses extra data· 2022-05-02
7
best: 73 (CLIP)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonLSMDC
video-to-text R@1· uses extra data· 2022-05-02
24.5
best: 46.7 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonLSMDC
video-to-text R@10· uses extra data· 2022-05-02
55.8
best: 91.8 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonLSMDC
video-to-text R@5· uses extra data· 2022-05-02
46.4
best: 71.8 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSVD
text-to-video Mean Rank· uses extra data· 2022-05-02
8.4
best: 23.1 (Collaborative Experts)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSVD
text-to-video Median Rank· uses extra data· 2022-05-02
1
best: 6 (SSML)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSVD
text-to-video R@1· uses extra data· 2022-05-02
50.6
best: 61.4 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSVD
text-to-video R@10· uses extra data· 2022-05-02
88.4
best: 90.3 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSVD
text-to-video R@5· uses extra data· 2022-05-02
80.3
best: 87.6 (CAMoE)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSVD
video-to-text Mean Rank· uses extra data· 2022-05-02
3
best: 7.6 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSVD
video-to-text Median Rank· uses extra data· 2022-05-02
1
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSVD
video-to-text R@1· uses extra data· 2022-05-02
68.4
best: 85.2 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSVD
video-to-text R@10· uses extra data· 2022-05-02
95
best: 97.1 (PAU)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
VideoonMSVD
video-to-text R@5· uses extra data· 2022-05-02
90.1
best: 94.5 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSR-VTT-1kA
text-to-video Mean Rank· uses extra data· 2022-05-02
13.8
best: 28.2 (Collaborative Experts)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSR-VTT-1kA
text-to-video Median Rank· uses extra data· 2022-05-02
2
best: 13 (JSFusion)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2022-05-02
48.4
best: 62.9 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2022-05-02
82
best: 90.8 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSR-VTT-1kA
text-to-video R@5· uses extra data· 2022-05-02
73.8
best: 84.5 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSR-VTT-1kA
video-to-text Mean Rank· uses extra data· 2022-05-02
10.2
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSR-VTT-1kA
video-to-text Median Rank· uses extra data· 2022-05-02
2
best: 5 (CLIP)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSR-VTT-1kA
video-to-text R@1· uses extra data· 2022-05-02
47.7
best: 64.8 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSR-VTT-1kA
video-to-text R@10· uses extra data· 2022-05-02
83.3
best: 91.1 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSR-VTT-1kA
video-to-text R@5· uses extra data· 2022-05-02
75
best: 783 (PIDRo)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonActivityNet
text-to-video Mean Rank· uses extra data· 2022-05-02
5.7
best: 23.1 (Collaborative Experts)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonActivityNet
text-to-video Median Rank· uses extra data· 2022-05-02
2
best: 6 (Collaborative Experts)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonActivityNet
text-to-video R@1· uses extra data· 2022-05-02
46.2
best: 74.1 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonActivityNet
text-to-video R@10· uses extra data· 2022-05-02
87.6
best: 96.1 (GRAM)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonActivityNet
text-to-video R@5· uses extra data· 2022-05-02
77
best: 90.9 (VAST)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonActivityNet
video-to-text R@1· uses extra data· 2022-05-02
46.7
best: 69.7 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonActivityNet
video-to-text R@10· uses extra data· 2022-05-02
88
best: 95.4 (GRAM)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonActivityNet
video-to-text R@5· uses extra data· 2022-05-02
77.1
best: 89.1 (UMT-L (ViT-L/16))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonLSMDC
text-to-video Mean Rank· uses extra data· 2022-05-02
47.3
best: 58 (CLIP4Clip)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonLSMDC
text-to-video Median Rank· uses extra data· 2022-05-02
8
best: 56.5 (CLIP)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonLSMDC
text-to-video R@1· uses extra data· 2022-05-02
24.2
best: 46.4 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonLSMDC
text-to-video R@10· uses extra data· 2022-05-02
55.9
best: 92.8 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonLSMDC
text-to-video R@5· uses extra data· 2022-05-02
46.2
best: 80.1 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonLSMDC
video-to-text Mean Rank· uses extra data· 2022-05-02
41.3
best: 48.9 (HunYuan_tvr)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonLSMDC
video-to-text Median Rank· uses extra data· 2022-05-02
7
best: 73 (CLIP)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonLSMDC
video-to-text R@1· uses extra data· 2022-05-02
24.5
best: 46.7 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonLSMDC
video-to-text R@10· uses extra data· 2022-05-02
55.8
best: 91.8 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonLSMDC
video-to-text R@5· uses extra data· 2022-05-02
46.4
best: 71.8 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSVD
text-to-video Mean Rank· uses extra data· 2022-05-02
8.4
best: 23.1 (Collaborative Experts)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSVD
text-to-video Median Rank· uses extra data· 2022-05-02
1
best: 6 (SSML)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSVD
text-to-video R@1· uses extra data· 2022-05-02
50.6
best: 61.4 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSVD
text-to-video R@10· uses extra data· 2022-05-02
88.4
best: 90.3 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSVD
text-to-video R@5· uses extra data· 2022-05-02
80.3
best: 87.6 (CAMoE)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSVD
video-to-text Mean Rank· uses extra data· 2022-05-02
3
best: 7.6 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSVD
video-to-text Median Rank· uses extra data· 2022-05-02
1
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSVD
video-to-text R@1· uses extra data· 2022-05-02
68.4
best: 85.2 (InternVideo2-6B)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSVD
video-to-text R@10· uses extra data· 2022-05-02
95
best: 97.1 (PAU)
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823
Video RetrievalonMSVD
video-to-text R@5· uses extra data· 2022-05-02
90.1
best: 94.5 (HunYuan_tvr (huge))
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval arXiv:2205.00823