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/ALPRO

ALPRO

Reported on 18 benchmarks across 4 tasks · 1 paper · 2 SOTA

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

Computer Vision16 results

Zero-Shot Video RetrievalonDiDeMo
text-to-video R@1· 2021-12-17
23.8
best: 57.9 (InternVideo2-6B)
SOTA
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
VideoonDiDeMo
text-to-video Median Rank· uses extra data· 2021-12-17
3
best: 8.3 (Collaborative Experts)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
VideoonDiDeMo
text-to-video R@1· uses extra data· 2021-12-17
35.9
best: 74.2 (InternVideo2-6B)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
VideoonDiDeMo
text-to-video R@10· uses extra data· 2021-12-17
78.8
best: 94.2 (vid-TLDR (UMT-L))
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
VideoonDiDeMo
text-to-video R@5· uses extra data· 2021-12-17
67.5
best: 91.2 (vid-TLDR (UMT-L))
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Video RetrievalonDiDeMo
text-to-video Median Rank· uses extra data· 2021-12-17
3
best: 8.3 (Collaborative Experts)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2021-12-17
35.9
best: 74.2 (InternVideo2-6B)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Video RetrievalonDiDeMo
text-to-video R@10· uses extra data· 2021-12-17
78.8
best: 94.2 (vid-TLDR (UMT-L))
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Video RetrievalonDiDeMo
text-to-video R@5· uses extra data· 2021-12-17
67.5
best: 91.2 (vid-TLDR (UMT-L))
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Zero-Shot Video RetrievalonMSR-VTT
text-to-video Median Rank· 2021-12-17
8
best: 66 (MMT)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@1· 2021-12-17
24.1
best: 55.9 (InternVideo2-6B)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@10· 2021-12-17
55.4
best: 85.1 (InternVideo2-6B)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@5· 2021-12-17
44.7
best: 78.3 (InternVideo2-6B)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Zero-Shot Video RetrievalonDiDeMo
text-to-video Median Rank· 2021-12-17
6
best: 7 (LaT)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Zero-Shot Video RetrievalonDiDeMo
text-to-video R@10· 2021-12-17
57.9
best: 85.1 (InternVideo2-1B)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Zero-Shot Video RetrievalonDiDeMo
text-to-video R@5· 2021-12-17
47.3
best: 80 (InternVideo2-6B)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583

Natural Language Processing2 results

Visual Question Answering (VQA)onMSRVTT-QA
Accuracy· uses extra data· 2021-12-17
0.421
best: 0.496 (VLAB)
SOTA
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583
Visual Question Answering (VQA)onMSVD-QA
Accuracy· uses extra data· 2021-12-17
0.459
best: 0.61 (VLAB)
Align and Prompt: Video-and-Language Pre-training with Entity Prompts arXiv:2112.09583