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/PEVL

PEVL

Reported on 24 benchmarks across 6 tasks · 1 paper · 23 SOTA

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

Computer Vision12 results

Scene ParsingonVisual Genome
R@100· 2022-05-23
66.3
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Scene ParsingonVisual Genome
R@50· 2022-05-23
64.4
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Scene ParsingonVisual Genome
mR@100· 2022-05-23
23.5
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Scene ParsingonVisual Genome
mR@50· 2022-05-23
21.7
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Visual Relationship DetectiononVisual Genome
R@100· 2022-05-23
66.3
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Visual Relationship DetectiononVisual Genome
R@50· 2022-05-23
64.4
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Visual Relationship DetectiononVisual Genome
mR@100· 2022-05-23
23.5
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Visual Relationship DetectiononVisual Genome
mR@50· 2022-05-23
21.7
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Scene UnderstandingonVisual Genome
R@100· 2022-05-23
66.3
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Scene UnderstandingonVisual Genome
R@50· 2022-05-23
64.4
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Scene UnderstandingonVisual Genome
mR@100· 2022-05-23
23.5
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Scene UnderstandingonVisual Genome
mR@50· 2022-05-23
21.7
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169

Reasoning6 results

Visual ReasoningonVCR (Q-AR) dev
Accuracy· 2022-05-23
57.8
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Visual ReasoningonVCR (Q-A) test
Accuracy· 2022-05-23
76
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Visual ReasoningonVCR (Q-AR) test
Accuracy· 2022-05-23
58.6
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Visual ReasoningonVCR (QA-R) dev
Accuracy· 2022-05-23
76.4
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Visual ReasoningonVCR (Q-A) dev
Accuracy· 2022-05-23
75.1
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Visual ReasoningonVCR (QA-R) test
Accuracy· 2022-05-23
76.7
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169

Audio4 results

2D Semantic SegmentationonVisual Genome
R@100· 2022-05-23
66.3
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
2D Semantic SegmentationonVisual Genome
R@50· 2022-05-23
64.4
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
2D Semantic SegmentationonVisual Genome
mR@100· 2022-05-23
23.5
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
2D Semantic SegmentationonVisual Genome
mR@50· 2022-05-23
21.7
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169

Natural Language Processing2 results

Phrase GroundingonFlickr30k Entities Dev
R@1· 2022-05-23
84.1
best: 87.1 (Fiber-B)
SOTA
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169
Phrase GroundingonFlickr30k Entities Test
R@1· uses extra data· 2022-05-23
84.4
best: 87.7 (GLIPv2)
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models arXiv:2205.11169