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/3SHNet

3SHNet

Reported on 39 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Miscellaneous26 results

Image Retrieval with Multi-Modal QueryonMSCOCO
Image-to-text R@1· 2024-04-26
85.8
SOTA
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonMSCOCO
Image-to-text R@1· 2024-04-26
85.8
SOTA
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@1· 2024-04-26
87.1
best: 98.8 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@10· 2024-04-26
99.2
best: 100 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@5· 2024-04-26
98.2
best: 100 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@1· 2024-04-26
69.5
best: 93.3 (ERNIE-ViL 2.0)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@10· 2024-04-26
94.7
best: 99.8 (ERNIE-ViL 2.0)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@5· 2024-04-26
91
best: 99.5 (M2-Encoder)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@1· 2024-04-26
67.9
best: 84.8 (BEiT-3)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@10· 2024-04-26
95.4
best: 98.5 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@5· 2024-04-26
90.5
best: 96.5 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@1· 2024-04-26
50.3
best: 68 (VAST)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@10· 2024-04-26
87.7
best: 92.8 (VAST)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@5· 2024-04-26
79.3
best: 92.8 (BEiT-3)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonFlickr30k
Image-to-text R@1· 2024-04-26
87.1
best: 98.8 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonFlickr30k
Image-to-text R@10· 2024-04-26
99.2
best: 100 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonFlickr30k
Image-to-text R@5· 2024-04-26
98.2
best: 100 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@1· 2024-04-26
69.5
best: 93.3 (ERNIE-ViL 2.0)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@10· 2024-04-26
94.7
best: 99.8 (ERNIE-ViL 2.0)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@5· 2024-04-26
91
best: 99.4 (ERNIE-ViL 2.0)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@1· 2024-04-26
67.9
best: 84.8 (BEiT-3)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@10· 2024-04-26
95.4
best: 98.5 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@5· 2024-04-26
90.5
best: 96.5 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@1· 2024-04-26
50.3
best: 68 (VAST)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@10· 2024-04-26
87.7
best: 92.8 (VAST)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@5· 2024-04-26
79.3
best: 92.8 (BEiT-3)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273

Natural Language Processing13 results

Cross-Modal RetrievalonMSCOCO
Image-to-text R@1· 2024-04-26
85.8
SOTA
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonFlickr30k
Image-to-text R@1· 2024-04-26
87.1
best: 98.8 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonFlickr30k
Image-to-text R@10· 2024-04-26
99.2
best: 100 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonFlickr30k
Image-to-text R@5· 2024-04-26
98.2
best: 100 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonFlickr30k
Text-to-image R@1· 2024-04-26
69.5
best: 93.3 (ERNIE-ViL 2.0)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonFlickr30k
Text-to-image R@10· 2024-04-26
94.7
best: 99.8 (ERNIE-ViL 2.0)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonFlickr30k
Text-to-image R@5· 2024-04-26
91
best: 99.4 (ERNIE-ViL 2.0)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@1· 2024-04-26
67.9
best: 84.8 (BEiT-3)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@10· 2024-04-26
95.4
best: 98.5 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@5· 2024-04-26
90.5
best: 96.5 (X2-VLM (large))
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@1· 2024-04-26
50.3
best: 68 (VAST)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@10· 2024-04-26
87.7
best: 92.8 (VAST)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@5· 2024-04-26
79.3
best: 92.8 (BEiT-3)
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting arXiv:2404.17273