Papers › Align and Attend: Multimodal Summarization with Dual Contrastive Losses
Align and Attend: Multimodal Summarization with Dual Contrastive Losses
Bo He, Jun Wang, JieLin Qiu, Trung Bui, Abhinav Shrivastava, Zhaowen Wang
The goal of multimodal summarization is to extract the most important information from different modalities to form output summaries. Unlike the unimodal summarization, the multimodal summarization task explicitly leverages cross-modal information to help generate more reliable and high-quality summaries. However, existing methods fail to leverage the temporal correspondence between different modalities and ignore the intrinsic correlation between different samples. To address this issue, we introduce Align and Attend Multimodal Summarization (A2Summ), a unified multimodal transformer-based model which can effectively align and attend the multimodal input. In addition, we propose two novel contrastive losses to model both inter-sample and intra-sample correlations. Extensive experiments on two standard video summarization datasets (TVSum and SumMe) and two multimodal summarization datasets (Daily Mail and CNN) demonstrate the superiority of A2Summ, achieving state-of-the-art performances on all datasets. Moreover, we collected a large-scale multimodal summarization dataset BLiSS, which contains livestream videos and transcribed texts with annotated summaries. Our code and dataset are publicly available at ~https://boheumd.github.io/A2Summ/.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2303.07284", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2303.07284")
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Extractive Text Summarization | CNN / Daily Mail | A2Summ | ROUGE-1 | 44.11 | #4 of 15 | Archive leaderboard | report |
| Extractive Text Summarization | CNN / Daily Mail | A2Summ | ROUGE-2 | 20.31 | #4 of 15 | Archive leaderboard | report |
| Extractive Text Summarization | CNN / Daily Mail | A2Summ | ROUGE-L | 35.92 | #4 of 15 | Archive leaderboard | report |
| Supervised Video Summarization | SumMe | A2Summ | F1-score (Canonical) | 55.0 | #3 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | SumMe | A2Summ | Kendall's Tau | 0.108 | #3 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | SumMe | A2Summ | Spearman's Rho | 0.129 | #3 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | TvSum | A2Summ | F1-score (Canonical) | 63.4 | #6 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | TvSum | A2Summ | Kendall's Tau | 0.137 | #6 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | TvSum | A2Summ | Spearman's Rho | 0.165 | #6 of 21 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections