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/Dual-Path (ResNet)

Dual-Path (ResNet)

Reported on 30 benchmarks across 3 tasks · 2 papers · 24 SOTA

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

Miscellaneous20 results

Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@10· 2017-11-15
89.5
best: 100 (X2-VLM (large))
SOTA
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@10· 2017-11-15
80.9
best: 99.8 (ERNIE-ViL 2.0)
SOTA
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535
Cross-Modal Information RetrievalonFlickr30k
Image-to-text R@10· 2017-11-15
89.5
best: 100 (X2-VLM (large))
SOTA
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@10· 2017-11-15
80.9
best: 99.8 (ERNIE-ViL 2.0)
SOTA
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@1· 2014-12-07
41.2
best: 84.8 (BEiT-3)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@10· 2014-12-07
81.1
best: 98.5 (X2-VLM (large))
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@5· 2014-12-07
70.5
best: 96.5 (X2-VLM (large))
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@1· 2014-12-07
25.3
best: 68 (VAST)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@10· 2014-12-07
66.4
best: 92.8 (VAST)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@5· 2014-12-07
53.4
best: 92.8 (BEiT-3)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@1· 2014-12-07
41.2
best: 84.8 (BEiT-3)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@10· 2014-12-07
81.1
best: 98.5 (X2-VLM (large))
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@5· 2014-12-07
70.5
best: 96.5 (X2-VLM (large))
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@1· 2014-12-07
25.3
best: 68 (VAST)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@10· 2014-12-07
66.4
best: 92.8 (VAST)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@5· 2014-12-07
53.4
best: 92.8 (BEiT-3)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@1· 2017-11-15
39.1
best: 93.3 (ERNIE-ViL 2.0)
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@5· 2017-11-15
69.2
best: 99.5 (M2-Encoder)
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@1· 2017-11-15
39.1
best: 93.3 (ERNIE-ViL 2.0)
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@5· 2017-11-15
69.2
best: 99.4 (ERNIE-ViL 2.0)
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535

Natural Language Processing10 results

Cross-Modal RetrievalonFlickr30k
Image-to-text R@10· 2017-11-15
89.5
best: 100 (X2-VLM (large))
SOTA
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535
Cross-Modal RetrievalonFlickr30k
Text-to-image R@10· 2017-11-15
80.9
best: 99.8 (ERNIE-ViL 2.0)
SOTA
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@1· 2014-12-07
41.2
best: 84.8 (BEiT-3)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@10· 2014-12-07
81.1
best: 98.5 (X2-VLM (large))
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@5· 2014-12-07
70.5
best: 96.5 (X2-VLM (large))
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@1· 2014-12-07
25.3
best: 68 (VAST)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@10· 2014-12-07
66.4
best: 92.8 (VAST)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@5· 2014-12-07
53.4
best: 92.8 (BEiT-3)
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Cross-Modal RetrievalonFlickr30k
Text-to-image R@1· 2017-11-15
39.1
best: 93.3 (ERNIE-ViL 2.0)
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535
Cross-Modal RetrievalonFlickr30k
Text-to-image R@5· 2017-11-15
69.2
best: 99.4 (ERNIE-ViL 2.0)
Dual-Path Convolutional Image-Text Embeddings with Instance Loss arXiv:1711.05535