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/VideoCLIP

VideoCLIP

Reported on 39 benchmarks across 9 tasks · 1 paper · 29 SOTA

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

Computer Vision32 results

VideoonCrossTask
Recall· uses extra data· 2021-09-28
47.3
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
VideoonYouCook2
text-to-video R@1· uses extra data· 2021-09-28
32.2
best: 50.4 (VAST)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
VideoonYouCook2
text-to-video R@10· uses extra data· 2021-09-28
75
best: 80.8 (VAST)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
VideoonYouCook2
text-to-video R@5· uses extra data· 2021-09-28
62.6
best: 74.3 (VAST)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Temporal Action LocalizationonCrossTask
Recall· uses extra data· 2021-09-28
47.3
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Action LocalizationonCrossTask
Recall· uses extra data· 2021-09-28
47.3
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Video RetrievalonYouCook2
text-to-video R@1· uses extra data· 2021-09-28
32.2
best: 50.4 (VAST)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Video RetrievalonYouCook2
text-to-video R@10· uses extra data· 2021-09-28
75
best: 80.8 (VAST)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Video RetrievalonYouCook2
text-to-video R@5· uses extra data· 2021-09-28
62.6
best: 74.3 (VAST)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Long Video Retrieval (Background Removed)onYouCook2
Cap. Avg. R@1· 2021-09-28
74.5
best: 75.5 (Norton)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Long Video Retrieval (Background Removed)onYouCook2
Cap. Avg. R@10· 2021-09-28
97.9
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Long Video Retrieval (Background Removed)onYouCook2
Cap. Avg. R@5· 2021-09-28
94.5
best: 95 (Norton)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Long Video Retrieval (Background Removed)onYouCook2
DTW R@1· 2021-09-28
56
best: 88.7 (Norton)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Long Video Retrieval (Background Removed)onYouCook2
DTW R@10· 2021-09-28
89.9
best: 99.5 (Norton)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Long Video Retrieval (Background Removed)onYouCook2
DTW R@5· 2021-09-28
96.3
best: 98.8 (Norton)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Long Video Retrieval (Background Removed)onYouCook2
OTAM R@1· 2021-09-28
52.8
best: 88.9 (Norton)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Long Video Retrieval (Background Removed)onYouCook2
OTAM R@10· 2021-09-28
89.2
best: 99.5 (Norton)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Long Video Retrieval (Background Removed)onYouCook2
OTAM R@5· 2021-09-28
95
best: 98.4 (Norton)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Zero-Shot Video RetrievalonDiDeMo
text-to-video R@5· 2021-09-28
46.9
best: 80 (InternVideo2-6B)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Zero-Shot Video RetrievalonYouCook2
text-to-video R@1· 2021-09-28
22.7
best: 26.1 (OmniVec2)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Zero-Shot Video RetrievalonYouCook2
text-to-video R@10· 2021-09-28
63.1
best: 70.8 (OmniVec2)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Zero-Shot Video RetrievalonYouCook2
text-to-video R@5· 2021-09-28
50.4
best: 54.1 (OmniVec2)
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
VideoonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2021-09-28
30.9
best: 62.9 (HunYuan_tvr (huge))
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
VideoonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2021-09-28
66.8
best: 90.8 (HunYuan_tvr (huge))
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
VideoonMSR-VTT-1kA
text-to-video R@5· uses extra data· 2021-09-28
55.4
best: 84.5 (HunYuan_tvr (huge))
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Video RetrievalonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2021-09-28
30.9
best: 62.9 (HunYuan_tvr (huge))
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Video RetrievalonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2021-09-28
66.8
best: 90.8 (HunYuan_tvr (huge))
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Video RetrievalonMSR-VTT-1kA
text-to-video R@5· uses extra data· 2021-09-28
55.4
best: 84.5 (HunYuan_tvr (huge))
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@1· 2021-09-28
10.4
best: 55.9 (InternVideo2-6B)
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@10· 2021-09-28
30
best: 85.1 (InternVideo2-6B)
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@5· 2021-09-28
22.2
best: 78.3 (InternVideo2-6B)
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Zero-Shot Video RetrievalonDiDeMo
text-to-video R@1· 2021-09-28
16.6
best: 57.9 (InternVideo2-6B)
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084

Natural Language Processing6 results

Relation ExtractiononVinoground
Group Score· 2021-09-28
1.2
best: 35 (GPT-4o (CoT))
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Relation ExtractiononVinoground
Text Score· 2021-09-28
17
best: 59.2 (GPT-4o (CoT))
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Relation ExtractiononVinoground
Video Score· 2021-09-28
2.8
best: 51 (GPT-4o (CoT))
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Temporal Relation ExtractiononVinoground
Group Score· 2021-09-28
1.2
best: 35 (GPT-4o (CoT))
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Temporal Relation ExtractiononVinoground
Text Score· 2021-09-28
17
best: 59.2 (GPT-4o (CoT))
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084
Temporal Relation ExtractiononVinoground
Video Score· 2021-09-28
2.8
best: 51 (GPT-4o (CoT))
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084

Methodology1 result

Zero-Shot LearningonCrossTask
Recall· uses extra data· 2021-09-28
47.3
SOTA
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding arXiv:2109.14084