{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/align-and-attend-multimodal-summarization","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","arxiv_id":"2303.07284","date":"2023-03-13","proceeding":"CVPR 2023 1","authors":["Bo He","Jun Wang","JieLin Qiu","Trung Bui","Abhinav Shrivastava","Zhaowen Wang"],"abstract":"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 ~\\url{https://boheumd.github.io/A2Summ/}.","url_abs":"https://arxiv.org/abs/2303.07284v3","url_pdf":"https://arxiv.org/pdf/2303.07284v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"align-and-attend-multimodal-summarization","repo_url":"https://github.com/boheumd/A2Summ","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"align-and-attend-multimodal-summarization","repo_url":"https://github.com/thswodnjs3/CSTA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"extractive-document-summarization","task_name":"Extractive Text Summarization"},{"task_slug":"supervised-video-summarization","task_name":"Supervised Video Summarization"},{"task_slug":"video-summarization","task_name":"Video Summarization"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"fail","method_name":"fail"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/extractive-document-summarization-on-cnn","task":"Extractive Text Summarization","dataset":"CNN / Daily Mail","model":"A2Summ","rank_in_archive_order":4,"of":15,"metrics":{"ROUGE-1":"44.11","ROUGE-2":"20.31","ROUGE-L":"35.92"},"uses_additional_data":false},{"leaderboard":"/sota/supervised-video-summarization-on-summe","task":"Supervised Video Summarization","dataset":"SumMe","model":"A2Summ","rank_in_archive_order":3,"of":21,"metrics":{"F1-score (Canonical)":"55.0","Kendall's Tau":"0.108","Spearman's Rho":"0.129"},"uses_additional_data":false},{"leaderboard":"/sota/supervised-video-summarization-on-tvsum","task":"Supervised Video Summarization","dataset":"TvSum","model":"A2Summ","rank_in_archive_order":6,"of":21,"metrics":{"F1-score (Canonical)":"63.4","Kendall's Tau":"0.137","Spearman's Rho":"0.165"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.07284","atlas_url":"https://app.syntology.ai/?focus=2303.07284","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2303.07284"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2303.07284\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2303.07284"},"call":"get_concepts_for_paper(arxiv_id=\"2303.07284\")"}],"by_repo":[{"repo":"boheumd/A2Summ","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"thswodnjs3/CSTA","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2405.11905"],"harvested_for_calls":[{"arxiv_id":"2405.11905","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.11905"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.11905\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d674d9b57da7d5b2ba0e1cc21d519d33a30f395c1253a7b579c24949f3838460","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}