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/GRAM

GRAM

Reported on 48 benchmarks across 3 tasks · 1 paper · 16 SOTA

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

Computer Vision48 results

VideoonVATEX
text-to-video R@1· uses extra data· 2024-12-16
87.7
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonVATEX
text-to-video R@10· uses extra data· 2024-12-16
100
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonVATEX
video-to-text R@10· uses extra data· 2024-12-16
100
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonActivityNet
text-to-video R@10· uses extra data· 2024-12-16
96.1
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonActivityNet
video-to-text R@10· uses extra data· 2024-12-16
95.4
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonMSR-VTT
text-to-video R@1· uses extra data· 2024-12-16
64
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonMSR-VTT
video-to-text R@1· uses extra data· 2024-12-16
64.8
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonVATEX
text-to-video R@1· uses extra data· 2024-12-16
87.7
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonVATEX
text-to-video R@10· uses extra data· 2024-12-16
100
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonVATEX
video-to-text R@10· uses extra data· 2024-12-16
100
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonActivityNet
text-to-video R@10· uses extra data· 2024-12-16
96.1
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonActivityNet
video-to-text R@10· uses extra data· 2024-12-16
95.4
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonMSR-VTT
text-to-video R@1· uses extra data· 2024-12-16
64
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonMSR-VTT
video-to-text R@1· uses extra data· 2024-12-16
64.8
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonVATEX
text-to-video R@1· uses extra data· 2024-12-16
83.9
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonVATEX
text-to-video R@10· uses extra data· 2024-12-16
99.5
SOTA
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonVATEX
video-to-text R@1· uses extra data· 2024-12-16
84.6
best: 89.3 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonActivityNet
text-to-video R@1· uses extra data· 2024-12-16
69.9
best: 74.1 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonActivityNet
video-to-text R@1· uses extra data· 2024-12-16
66.9
best: 69.7 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonDiDeMo
text-to-video R@1· uses extra data· 2024-12-16
67.3
best: 74.2 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonDiDeMo
text-to-video R@10· uses extra data· 2024-12-16
90.1
best: 94.2 (vid-TLDR (UMT-L))
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonDiDeMo
video-to-text R@1· uses extra data· 2024-12-16
63.5
best: 71.9 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonDiDeMo
video-to-text R@10· uses extra data· 2024-12-16
91.6
best: 93.8 (vid-TLDR (UMT-L))
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonMSR-VTT
text-to-video R@10· uses extra data· 2024-12-16
89.3
best: 89.6 (VAST)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
VideoonMSR-VTT
video-to-text R@10· uses extra data· 2024-12-16
91.5
best: 92.8 (CAMoE)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonVATEX
video-to-text R@1· uses extra data· 2024-12-16
84.6
best: 89.3 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonActivityNet
text-to-video R@1· uses extra data· 2024-12-16
69.9
best: 74.1 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonActivityNet
video-to-text R@1· uses extra data· 2024-12-16
66.9
best: 69.7 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2024-12-16
67.3
best: 74.2 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonDiDeMo
text-to-video R@10· uses extra data· 2024-12-16
90.1
best: 94.2 (vid-TLDR (UMT-L))
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonDiDeMo
video-to-text R@1· uses extra data· 2024-12-16
63.5
best: 71.9 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonDiDeMo
video-to-text R@10· uses extra data· 2024-12-16
91.6
best: 93.8 (vid-TLDR (UMT-L))
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonMSR-VTT
text-to-video R@10· uses extra data· 2024-12-16
89.3
best: 89.6 (VAST)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Video RetrievalonMSR-VTT
video-to-text R@10· uses extra data· 2024-12-16
91.5
best: 92.8 (CAMoE)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonVATEX
video-to-text R@1· uses extra data· 2024-12-16
82.7
best: 85.4 (InternVideo2-1B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonVATEX
video-to-text R@10· uses extra data· 2024-12-16
99
best: 99.3 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@1· uses extra data· 2024-12-16
54.8
best: 55.9 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@10· uses extra data· 2024-12-16
83.9
best: 85.1 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonMSR-VTT
video-to-text R@1· uses extra data· 2024-12-16
52.9
best: 53.7 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonMSR-VTT
video-to-text R@10· uses extra data· 2024-12-16
82.9
best: 84.1 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2024-12-16
54.2
best: 57.9 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonDiDeMo
text-to-video R@10· uses extra data· 2024-12-16
80.7
best: 85.1 (InternVideo2-1B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonDiDeMo
video-to-text R@1· uses extra data· 2024-12-16
52.3
best: 57.1 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonDiDeMo
video-to-text R@10· uses extra data· 2024-12-16
80.3
best: 85 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonActivityNet
text-to-video R@1· uses extra data· 2024-12-16
59
best: 63.2 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonActivityNet
text-to-video R@10· uses extra data· 2024-12-16
91.2
best: 92.5 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonActivityNet
video-to-text R@1· uses extra data· 2024-12-16
50.9
best: 56.5 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959
Zero-Shot Video RetrievalonActivityNet
video-to-text R@10· uses extra data· 2024-12-16
85.8
best: 90.3 (InternVideo2-6B)
Gramian Multimodal Representation Learning and Alignment arXiv:2412.11959