{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/video-summarization-based-on-video-text","title":"Progressive Video Summarization via Multimodal Self-supervised Learning","arxiv_id":"2201.02494","date":"2022-01-07","proceeding":null,"authors":["Li Haopeng","Ke Qiuhong","Gong Mingming","Tom Drummond"],"abstract":"Modern video summarization methods are based on deep neural networks that require a large amount of annotated data for training. However, existing datasets for video summarization are small-scale, easily leading to over-fitting of the deep models. Considering that the annotation of large-scale datasets is time-consuming, we propose a multimodal self-supervised learning framework to obtain semantic representations of videos, which benefits the video summarization task. Specifically, the self-supervised learning is conducted by exploring the semantic consistency between the videos and text in both coarse-grained and fine-grained fashions, as well as recovering masked frames in the videos. The multimodal framework is trained on a newly-collected dataset that consists of video-text pairs. Additionally, we introduce a progressive video summarization method, where the important content in a video is pinpointed progressively to generate better summaries. Extensive experiments have proved the effectiveness and superiority of our method in rank correlation coefficients and F-score.","url_abs":"https://arxiv.org/abs/2201.02494v4","url_pdf":"https://arxiv.org/pdf/2201.02494v4.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":"video-summarization-based-on-video-text","repo_url":"https://github.com/HopLee6/SSPVS-PyTorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"video-summarization-based-on-video-text","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":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"supervised-video-summarization","task_name":"Supervised Video Summarization"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"video-summarization","task_name":"Video Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/supervised-video-summarization-on-summe","task":"Supervised Video Summarization","dataset":"SumMe","model":"SSPVS(+Text)","rank_in_archive_order":10,"of":21,"metrics":{"F1-score (Canonical)":"50.7","Kendall's Tau":"0.192","Spearman's Rho":"0.257"},"uses_additional_data":false},{"leaderboard":"/sota/supervised-video-summarization-on-summe","task":"Supervised Video Summarization","dataset":"SumMe","model":"SSPVS","rank_in_archive_order":13,"of":21,"metrics":{"F1-score (Augmented)":"50.4","F1-score (Canonical)":"48.7","Kendall's Tau":"0.178","Spearman's Rho":"0.240"},"uses_additional_data":false},{"leaderboard":"/sota/supervised-video-summarization-on-tvsum","task":"Supervised Video Summarization","dataset":"TvSum","model":"SSPVS(+Text)","rank_in_archive_order":15,"of":21,"metrics":{"F1-score (Canonical)":"60.4","Kendall's Tau":"0.181","Spearman's Rho":"0.238"},"uses_additional_data":false},{"leaderboard":"/sota/supervised-video-summarization-on-tvsum","task":"Supervised Video Summarization","dataset":"TvSum","model":"SSPVS","rank_in_archive_order":16,"of":21,"metrics":{"F1-score (Augmented)":"61.8","F1-score (Canonical)":"60.3","Kendall's Tau":"0.177","Spearman's Rho":"0.233"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.02494","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}