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/A2Summ

A2Summ

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 Vision12 results

VideoonSumMe
F1-score (Canonical)· 2023-03-13
55
best: 57.1 (PGL-SUM (maximum learning capacity))
SOTA
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
Video SummarizationonSumMe
F1-score (Canonical)· 2023-03-13
55
best: 57.1 (PGL-SUM (maximum learning capacity))
SOTA
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
VideoonTvSum
F1-score (Canonical)· 2023-03-13
63.4
best: 67.5 (MAVS [DBLP:conf/mm/FengLKZ18])
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
VideoonTvSum
Kendall's Tau· 2023-03-13
0.137
best: 0.203 (DMASum)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
VideoonTvSum
Spearman's Rho· 2023-03-13
0.165
best: 0.267 (DMASum)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
VideoonSumMe
Kendall's Tau· 2023-03-13
0.108
best: 0.246 (CSTA)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
VideoonSumMe
Spearman's Rho· 2023-03-13
0.129
best: 0.274 (CSTA)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
Video SummarizationonTvSum
F1-score (Canonical)· 2023-03-13
63.4
best: 67.5 (MAVS [DBLP:conf/mm/FengLKZ18])
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
Video SummarizationonTvSum
Kendall's Tau· 2023-03-13
0.137
best: 0.203 (DMASum)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
Video SummarizationonTvSum
Spearman's Rho· 2023-03-13
0.165
best: 0.267 (DMASum)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
Video SummarizationonSumMe
Kendall's Tau· 2023-03-13
0.108
best: 0.246 (CSTA)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
Video SummarizationonSumMe
Spearman's Rho· 2023-03-13
0.129
best: 0.274 (CSTA)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284

Knowledge Base3 results

Text SummarizationonCNN / Daily Mail
ROUGE-1· 2023-03-13
44.11
best: 48.18 (Scrambled code + broken (alter))
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
Text SummarizationonCNN / Daily Mail
ROUGE-2· 2023-03-13
20.31
best: 24.02 (Pegasus)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
Text SummarizationonCNN / Daily Mail
ROUGE-L· 2023-03-13
35.92
best: 45.35 (Scrambled code + broken (alter))
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284

Natural Language Processing3 results

Extractive Text SummarizationonCNN / Daily Mail
ROUGE-1· 2023-03-13
44.11
best: 44.68 (HAHSum)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
Extractive Text SummarizationonCNN / Daily Mail
ROUGE-2· 2023-03-13
20.31
best: 21.3 (HAHSum)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284
Extractive Text SummarizationonCNN / Daily Mail
ROUGE-L· 2023-03-13
35.92
best: 40.75 (HAHSum)
Align and Attend: Multimodal Summarization with Dual Contrastive Losses arXiv:2303.07284