{"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":"/task/supervised-video-summarization","name":"Supervised Video Summarization","slug":"supervised-video-summarization","description_markdown":"**Supervised video summarization** rely on datasets with human-labeled ground-truth annotations (either in the form of video summaries, as in the case of the [SumMe](https://paperswithcode.com/dataset/summe) dataset, or in the form of frame-level importance scores, as in the case of the [TVSum](https://paperswithcode.com/dataset/tvsum-1) dataset), based on which they try to discover the underlying criterion for video frame/fragment selection and video summarization.\r\n\r\nSource: [Video Summarization Using Deep Neural Networks: A Survey](https://arxiv.org/abs/2101.06072)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":28,"papers_with_code":12,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/supervised-video-summarization-on-summe","slug":"supervised-video-summarization-on-summe","dataset":"SumMe","dataset_url":"/dataset/summe","rows_in_archive":21,"metrics":["F1-score (Canonical)","F1-score (Augmented)","Kendall's Tau","Spearman's Rho"],"first_row_in_archive_order":{"model":"PGL-SUM (maximum learning capacity)","paper_title":"Combining Global and Local Attention with Positional Encoding for Video Summarization","paper_url":"/paper/combining-global-and-local-attention-with","paper_date":"2021-12-01","arxiv_id":null,"code_links":[{"title":"e-apostolidis/PGL-SUM","url":"https://github.com/e-apostolidis/PGL-SUM"}],"syntology":null}},{"leaderboard":"/sota/supervised-video-summarization-on-tvsum","slug":"supervised-video-summarization-on-tvsum","dataset":"TvSum","dataset_url":"/dataset/tvsum","rows_in_archive":21,"metrics":["F1-score (Canonical)","F1-score (Augmented)","Kendall's Tau","Spearman's Rho"],"first_row_in_archive_order":{"model":"MAVS [DBLP:conf/mm/FengLKZ18]","paper_title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","paper_url":"/paper/supervised-video-summarization-via-multiple","paper_date":"2021-04-23","arxiv_id":"2104.11530","code_links":[{"title":"thswodnjs3/CSTA","url":"https://github.com/thswodnjs3/CSTA"},{"title":"TIBHannover/MSVA","url":"https://github.com/TIBHannover/MSVA"},{"title":"StevRamos/video_summarization","url":"https://github.com/StevRamos/video_summarization"}],"syntology":null}}],"datasets":[{"url":"/dataset/summe","name":"SumMe","full_name":"SumMe","num_papers_in_archive":146},{"url":"/dataset/tvsum","name":"TvSum","full_name":"TVSum: Summarizing Web Videos Using Titles","num_papers_in_archive":28},{"url":"/dataset/query-focused-video-summarization-dataset","name":"Query-Focused Video Summarization Dataset","full_name":"","num_papers_in_archive":4},{"url":"/dataset/mr-hisum","name":"Mr. HiSum","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/video-summarization","name":"Video Summarization"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":28,"of":28,"of_with_code":12,"tagged_in_all":28,"counts":{"archive_papers_tagged":28,"with_a_code_link":12,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":28,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/deep-reinforcement-learning-for-unsupervised","slug":"deep-reinforcement-learning-for-unsupervised","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","date":"2017-12-29","arxiv_id":"1801.00054","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-reinforcement-learning-for-unsupervised#ran","syntology_url":"https://syntology.ai/paper/1801.00054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.00054"}},"official":{"repos":["KaiyangZhou/vsumm-reinforce"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/supervised-video-summarization-via-multiple","slug":"supervised-video-summarization-via-multiple","title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","date":"2021-04-23","arxiv_id":"2104.11530","repositories_listed":3,"syntology":null},{"url":"/paper/test-time-training-for-out-of-distribution-1","slug":"test-time-training-for-out-of-distribution-1","title":"Test-Time Training with Self-Supervision for Generalization under Distribution Shifts","date":"2019-09-29","arxiv_id":"1909.13231","repositories_listed":3,"syntology":null},{"url":"/paper/align-and-attend-multimodal-summarization","slug":"align-and-attend-multimodal-summarization","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","date":"2023-03-13","arxiv_id":"2303.07284","repositories_listed":2,"syntology":null},{"url":"/paper/video-summarization-based-on-video-text","slug":"video-summarization-based-on-video-text","title":"Progressive Video Summarization via Multimodal Self-supervised Learning","date":"2022-01-07","arxiv_id":"2201.02494","repositories_listed":2,"syntology":null},{"url":"/paper/video-joint-modelling-based-on-hierarchical","slug":"video-joint-modelling-based-on-hierarchical","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","date":"2021-12-27","arxiv_id":"2112.13478","repositories_listed":2,"syntology":null},{"url":"/paper/csta-cnn-based-spatiotemporal-attention-for","slug":"csta-cnn-based-spatiotemporal-attention-for","title":"CSTA: CNN-based Spatiotemporal Attention for Video Summarization","date":"2024-05-20","arxiv_id":"2405.11905","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":7,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","sample_list":"/paper/csta-cnn-based-spatiotemporal-attention-for#ran","syntology_url":"https://syntology.ai/paper/2405.11905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11905"}},"official":{"repos":["thswodnjs3/CSTA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/combining-global-and-local-attention-with","slug":"combining-global-and-local-attention-with","title":"Combining Global and Local Attention with Positional Encoding for Video Summarization","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/clip-it-language-guided-video-summarization","slug":"clip-it-language-guided-video-summarization","title":"CLIP-It! Language-Guided Video Summarization","date":"2021-07-01","arxiv_id":"2107.00650","repositories_listed":1,"syntology":null},{"url":"/paper/self-attention-recurrent-summarization","slug":"self-attention-recurrent-summarization","title":"Self-Attention Recurrent Summarization Network with Reinforcement Learning for Video Summarization Task","date":"2021-06-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dsnet-a-flexible-detect-to-summarize-network","slug":"dsnet-a-flexible-detect-to-summarize-network","title":"DSNet: A Flexible Detect-to-Summarize Network for Video Summarization","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/discriminative-feature-learning-for","slug":"discriminative-feature-learning-for","title":"Discriminative Feature Learning for Unsupervised Video Summarization","date":"2018-11-24","arxiv_id":"1811.09791","repositories_listed":1,"syntology":null},{"url":null,"slug":"trim-a-self-supervised-video-summarization","title":"TRIM: A Self-Supervised Video Summarization Framework Maximizing Temporal Relative Information and Representativeness","date":"2025-06-25","arxiv_id":"2506.20588","repositories_listed":0,"syntology":null},{"url":null,"slug":"fulltransnet-full-transformer-with-local","title":"FullTransNet: Full Transformer with Local-Global Attention for Video Summarization","date":"2025-01-01","arxiv_id":"2501.00882","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-guided-self-supervised-video","title":"Language-Guided Self-Supervised Video Summarization Using Text Semantic Matching Considering the Diversity of the Video","date":"2024-05-14","arxiv_id":"2405.08890","repositories_listed":0,"syntology":null},{"url":"/paper/relational-reasoning-over-spatial-temporal","slug":"relational-reasoning-over-spatial-temporal","title":"Relational Reasoning Over Spatial-Temporal Graphs for Video Summarization","date":"2022-04-06","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/joint-video-summarization-and-moment","slug":"joint-video-summarization-and-moment","title":"Joint Video Summarization and Moment Localization by Cross-Task Sample Transfer","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-video-summarization-method-using-temporal","title":"A Stacking Ensemble Approach for Supervised Video Summarization","date":"2021-09-26","arxiv_id":"2109.12581","repositories_listed":0,"syntology":null},{"url":"/paper/hierarchical-multimodal-transformer-to","slug":"hierarchical-multimodal-transformer-to","title":"Hierarchical Multimodal Transformer to Summarize Videos","date":"2021-09-22","arxiv_id":"2109.10559","repositories_listed":0,"syntology":null},{"url":null,"slug":"use-of-affective-visual-information-for","title":"Use of Affective Visual Information for Summarization of Human-Centric Videos","date":"2021-07-08","arxiv_id":"2107.03783","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-good-is-a-video-summary-a-new","title":"How Good is a Video Summary? A New Benchmarking Dataset and Evaluation Framework Towards Realistic Video Summarization","date":"2021-01-26","arxiv_id":"2101.10514","repositories_listed":0,"syntology":null},{"url":"/paper/query-twice-dual-mixture-attention-meta","slug":"query-twice-dual-mixture-attention-meta","title":"Query Twice: Dual Mixture Attention Meta Learning for Video Summarization","date":"2020-08-19","arxiv_id":"2008.08360","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-video-summarization-by","title":"Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning","date":"2020-01-12","arxiv_id":"2001.05864","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-video-summarization-using","title":"Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web Prior","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-sequential-determinantal-point","title":"Improving Sequential Determinantal Point Processes for Supervised Video Summarization","date":"2018-07-28","arxiv_id":"1807.10957","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-local-is-the-local-diversity-reinforcing","title":"How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization","date":"2018-07-11","arxiv_id":"1807.04219","repositories_listed":0,"syntology":null},{"url":"/paper/video-summarization-with-attention-based","slug":"video-summarization-with-attention-based","title":"Video Summarization with Attention-Based Encoder-Decoder Networks","date":"2017-08-31","arxiv_id":"1708.09545","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-sequential-subset-selection-for","title":"Diverse Sequential Subset Selection for Supervised Video Summarization","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/supervised-video-summarization-on-summe","since_archive":"/sota/supervised-video-summarization-on-summe#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/supervised-video-summarization-on-tvsum","since_archive":"/sota/supervised-video-summarization-on-tvsum#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/task/supervised-video-summarization/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/supervised-video-summarization/papers/ran/1","json":"/task/supervised-video-summarization/papers/ran/1.json","rows":2}],"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"b2dca14e45a50e1f60210efd2c6c5879a112fb0cc96307b3e284dbf6fffe9671","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}