{"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":"/dataset/activitynet-captions","name":"ActivityNet Captions","full_name":null,"description_markdown":"The **ActivityNet Captions** dataset is built on ActivityNet v1.3 which includes 20k YouTube untrimmed videos with 100k caption annotations. The videos are 120 seconds long on average. Most of the videos contain over 3 annotated events with corresponding start/end time and human-written sentences, which contain 13.5 words on average. The number of videos in train/validation/test split is 10024/4926/5044, respectively.\r\n\r\nSource: [Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning](https://arxiv.org/abs/1804.00100)\r\nImage Source: [https://cs.stanford.edu/people/ranjaykrishna/densevid/](https://cs.stanford.edu/people/ranjaykrishna/densevid/)","description_withheld":null,"homepage":"https://cs.stanford.edu/people/ranjaykrishna/densevid/","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/dense-captioning-events-in-videos","title":"Dense-Captioning Events in Videos","first_author":"Ranjay Krishna","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Video Captioning","url":"/task/video-captioning","datasets_with_task":"/datasets/task/video-captioning"},{"name":"Dense Video Captioning","url":"/task/dense-video-captioning","datasets_with_task":"/datasets/task/dense-video-captioning"},{"name":"Natural Language Moment Retrieval","url":"/task/natural-language-moment-retrieval","datasets_with_task":"/datasets/task/natural-language-moment-retrieval"},{"name":"Temporal Action Proposal Generation","url":"/task/temporal-action-proposal-generation","datasets_with_task":"/datasets/task/temporal-action-proposal-generation"},{"name":"Partially Relevant Video Retrieval","url":"/task/partially-relevant-video-retrieval","datasets_with_task":"/datasets/task/partially-relevant-video-retrieval"},{"name":"Live Video Captioning","url":"/task/live-video-captioning","datasets_with_task":"/datasets/task/live-video-captioning"}],"languages":[],"variants":["ActivityNet Captions"],"data_loaders":[],"num_papers_in_archive":255,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/dense-video-captioning-on-activitynet","task":"Dense Video Captioning","dataset_variant":"ActivityNet Captions","rows":12,"metrics":["METEOR","BLEU-3","BLEU-4","CIDEr","SODA","DIV-1","DIV-2","RE-4","BLEU4","F1","Precision","Recall"],"first_row_in_archive_order":{"model":"Vid2Seq","paper":"/paper/vid2seq-large-scale-pretraining-of-a-visual","metrics":{"CIDEr":"28","METEOR":"17"},"code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic/tree/main/scenic/projects/vid2seq"},{"title":"antoyang/VidChapters","url":"https://github.com/antoyang/VidChapters"},{"title":"KastanDay/video-pretrained-transformer","url":"https://github.com/KastanDay/video-pretrained-transformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/natural-language-moment-retrieval-on","task":"Natural Language Moment Retrieval","dataset_variant":"ActivityNet Captions","rows":8,"metrics":["R@1,IoU=0.5","R@1,IoU=0.7","R@5,IoU=0.5","R@5,IoU=0.7"],"first_row_in_archive_order":{"model":"GVL (paragraph-level)","paper":"/paper/learning-grounded-vision-language","metrics":{"R@1,IoU=0.5":"60.67","R@1,IoU=0.7":"38.55"},"code_links":[{"title":"zjr2000/gvl","url":"https://github.com/zjr2000/gvl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-captioning-on-activitynet-captions","task":"Video Captioning","dataset_variant":"ActivityNet Captions","rows":5,"metrics":["BLEU4","BLEU-3","CIDEr","ROUGE-L","METEOR"],"first_row_in_archive_order":{"model":"VideoCoCa","paper":"/paper/video-text-modeling-with-zero-shot-transfer","metrics":{"BLEU4":"14.7","CIDEr":"39.3","ROUGE-L":"35.0"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/live-video-captioning-on-activitynet-captions","task":"Live Video Captioning","dataset_variant":"ActivityNet Captions","rows":1,"metrics":["Live Score"],"first_row_in_archive_order":{"model":"LVC","paper":"/paper/live-video-captioning","metrics":{"Live Score":"20.81"},"code_links":[{"title":"gramuah/lvc","url":"https://github.com/gramuah/lvc"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/partially-relevant-video-retrieval-on","task":"Partially Relevant Video Retrieval","dataset_variant":"ActivityNet Captions","rows":1,"metrics":["Recall@Sum"],"first_row_in_archive_order":{"model":"ms-sl","paper":"/paper/partially-relevant-video-retrieval","metrics":{"Recall@Sum":"140.1"},"code_links":[{"title":"HuiGuanLab/ms-sl","url":"https://github.com/HuiGuanLab/ms-sl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/temporal-action-proposal-generation-on-1","task":"Temporal Action Proposal Generation","dataset_variant":"ActivityNet Captions","rows":1,"metrics":["Average F1","Average Precision","Average Recall"],"first_row_in_archive_order":{"model":"BMT","paper":"/paper/a-better-use-of-audio-visual-cues-dense-video","metrics":{"Average F1":"60.27","Average Precision":"48.23","Average Recall":"80.31"},"code_links":[{"title":"v-iashin/video_features","url":"https://github.com/v-iashin/video_features"},{"title":"v-iashin/BMT","url":"https://github.com/v-iashin/BMT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":24,"of":24,"counts":{"papers_with_a_benchmark_row":24,"with_a_code_link":21,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":24,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":7,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/llava-mr-large-language-and-vision-assistant","slug":"llava-mr-large-language-and-vision-assistant","title":"LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval","date":"2024-11-21","arxiv_id":"2411.14505","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/live-video-captioning","slug":"live-video-captioning","title":"Live Video Captioning","date":"2024-06-20","arxiv_id":"2406.14206","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/do-you-remember-dense-video-captioning-with","slug":"do-you-remember-dense-video-captioning-with","title":"Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval","date":"2024-04-11","arxiv_id":"2404.07610","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ailab-kyunghee/cm2_dvc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/do-you-remember-dense-video-captioning-with#ran","syntology_url":"https://syntology.ai/paper/2404.07610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07610"}}}},{"paper":"/paper/unimd-towards-unifying-moment-retrieval-and","slug":"unimd-towards-unifying-moment-retrieval-and","title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","date":"2024-04-07","arxiv_id":"2404.04933","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vtimellm-empower-llm-to-grasp-video-moments","slug":"vtimellm-empower-llm-to-grasp-video-moments","title":"VTimeLLM: Empower LLM to Grasp Video Moments","date":"2023-11-30","arxiv_id":"2311.18445","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":4,"pointer_only_for_licence":11,"official":{"repos":["huangb23/vtimellm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vtimellm-empower-llm-to-grasp-video-moments#ran","syntology_url":"https://syntology.ai/paper/2311.18445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18445"}}}},{"paper":"/paper/unloc-a-unified-framework-for-video","slug":"unloc-a-unified-framework-for-video","title":"UnLoc: A Unified Framework for Video Localization Tasks","date":"2023-08-21","arxiv_id":"2308.11062","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/learning-grounded-vision-language","slug":"learning-grounded-vision-language","title":"Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos","date":"2023-03-11","arxiv_id":"2303.06378","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["zjr2000/gvl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-grounded-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.06378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06378"}}}},{"paper":"/paper/vid2seq-large-scale-pretraining-of-a-visual","slug":"vid2seq-large-scale-pretraining-of-a-visual","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","date":"2023-02-27","arxiv_id":"2302.14115","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/video-text-modeling-with-zero-shot-transfer","slug":"video-text-modeling-with-zero-shot-transfer","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","date":"2022-12-09","arxiv_id":"2212.04979","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vltint-visual-linguistic-transformer-in","slug":"vltint-visual-linguistic-transformer-in","title":"VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning","date":"2022-11-28","arxiv_id":"2211.15103","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/partially-relevant-video-retrieval","slug":"partially-relevant-video-retrieval","title":"Partially Relevant Video Retrieval","date":"2022-08-26","arxiv_id":"2208.12510","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vlcap-vision-language-with-contrastive","slug":"vlcap-vision-language-with-contrastive","title":"VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning","date":"2022-06-26","arxiv_id":"2206.12972","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/end-to-end-dense-video-captioning-with","slug":"end-to-end-dense-video-captioning-with","title":"End-to-End Dense Video Captioning with Parallel Decoding","date":"2021-08-17","arxiv_id":"2108.07781","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["ttengwang/pdvc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-dense-video-captioning-with#ran","syntology_url":"https://syntology.ai/paper/2108.07781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07781"}}}},{"paper":"/paper/global-object-proposals-for-improving-multi","slug":"global-object-proposals-for-improving-multi","title":"Global Object Proposals for Improving Multi-Sentence Video Descriptions","date":"2021-07-18","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tsp-temporally-sensitive-pretraining-of-video","slug":"tsp-temporally-sensitive-pretraining-of-video","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","date":"2020-11-23","arxiv_id":"2011.11479","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vlg-net-video-language-graph-matching-network","slug":"vlg-net-video-language-graph-matching-network","title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","date":"2020-11-19","arxiv_id":"2011.10132","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vlg-net-video-language-graph-matching-network#ran","syntology_url":"https://syntology.ai/paper/2011.10132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.10132"}}}},{"paper":"/paper/iperceive-applying-common-sense-reasoning-to-1","slug":"iperceive-applying-common-sense-reasoning-to-1","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering","date":"2020-11-16","arxiv_id":"2011.07735","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/coot-cooperative-hierarchical-transformer-for","slug":"coot-cooperative-hierarchical-transformer-for","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","date":"2020-11-01","arxiv_id":"2011.00597","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["gingsi/coot-videotext"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coot-cooperative-hierarchical-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2011.00597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.00597"}}}},{"paper":"/paper/dense-captioning-events-in-videos-sysu","slug":"dense-captioning-events-in-videos-sysu","title":"Dense-Captioning Events in Videos: SYSU Submission to ActivityNet Challenge 2020","date":"2020-06-21","arxiv_id":"2006.11693","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/team-ruc-aim3-technical-report-at-activitynet","slug":"team-ruc-aim3-technical-report-at-activitynet","title":"Team RUC_AIM3 Technical Report at Activitynet 2020 Task 2: Exploring Sequential Events Detection for Dense Video Captioning","date":"2020-06-14","arxiv_id":"2006.07896","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-better-use-of-audio-visual-cues-dense-video","slug":"a-better-use-of-audio-visual-cues-dense-video","title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer","date":"2020-05-17","arxiv_id":"2005.08271","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["v-iashin/BMT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-better-use-of-audio-visual-cues-dense-video#ran","syntology_url":"https://syntology.ai/paper/2005.08271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08271"}}}},{"paper":"/paper/mart-memory-augmented-recurrent-transformer","slug":"mart-memory-augmented-recurrent-transformer","title":"MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning","date":"2020-05-11","arxiv_id":"2005.05402","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["jayleicn/recurrent-transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mart-memory-augmented-recurrent-transformer#ran","syntology_url":"https://syntology.ai/paper/2005.05402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05402"}}}},{"paper":"/paper/dense-regression-network-for-video-grounding","slug":"dense-regression-network-for-video-grounding","title":"Dense Regression Network for Video Grounding","date":"2020-04-07","arxiv_id":"2004.03545","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modal-dense-video-captioning","slug":"multi-modal-dense-video-captioning","title":"Multi-modal Dense Video Captioning","date":"2020-03-17","arxiv_id":"2003.07758","rows_on_this_dataset":1,"code_links":4,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/llava-mr-large-language-and-vision-assistant","slug":"llava-mr-large-language-and-vision-assistant","title":"LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval","date":"2024-11-21","arxiv_id":"2411.14505","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/live-video-captioning","slug":"live-video-captioning","title":"Live Video Captioning","date":"2024-06-20","arxiv_id":"2406.14206","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/do-you-remember-dense-video-captioning-with","slug":"do-you-remember-dense-video-captioning-with","title":"Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval","date":"2024-04-11","arxiv_id":"2404.07610","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ailab-kyunghee/cm2_dvc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/do-you-remember-dense-video-captioning-with#ran","syntology_url":"https://syntology.ai/paper/2404.07610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07610"}}}},{"paper":"/paper/unimd-towards-unifying-moment-retrieval-and","slug":"unimd-towards-unifying-moment-retrieval-and","title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","date":"2024-04-07","arxiv_id":"2404.04933","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vtimellm-empower-llm-to-grasp-video-moments","slug":"vtimellm-empower-llm-to-grasp-video-moments","title":"VTimeLLM: Empower LLM to Grasp Video Moments","date":"2023-11-30","arxiv_id":"2311.18445","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":4,"pointer_only_for_licence":11,"official":{"repos":["huangb23/vtimellm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vtimellm-empower-llm-to-grasp-video-moments#ran","syntology_url":"https://syntology.ai/paper/2311.18445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18445"}}}},{"paper":"/paper/unloc-a-unified-framework-for-video","slug":"unloc-a-unified-framework-for-video","title":"UnLoc: A Unified Framework for Video Localization Tasks","date":"2023-08-21","arxiv_id":"2308.11062","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/learning-grounded-vision-language","slug":"learning-grounded-vision-language","title":"Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos","date":"2023-03-11","arxiv_id":"2303.06378","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["zjr2000/gvl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-grounded-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.06378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06378"}}}},{"paper":"/paper/vid2seq-large-scale-pretraining-of-a-visual","slug":"vid2seq-large-scale-pretraining-of-a-visual","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","date":"2023-02-27","arxiv_id":"2302.14115","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/video-text-modeling-with-zero-shot-transfer","slug":"video-text-modeling-with-zero-shot-transfer","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","date":"2022-12-09","arxiv_id":"2212.04979","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vltint-visual-linguistic-transformer-in","slug":"vltint-visual-linguistic-transformer-in","title":"VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning","date":"2022-11-28","arxiv_id":"2211.15103","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/partially-relevant-video-retrieval","slug":"partially-relevant-video-retrieval","title":"Partially Relevant Video Retrieval","date":"2022-08-26","arxiv_id":"2208.12510","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vlcap-vision-language-with-contrastive","slug":"vlcap-vision-language-with-contrastive","title":"VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning","date":"2022-06-26","arxiv_id":"2206.12972","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/end-to-end-dense-video-captioning-with","slug":"end-to-end-dense-video-captioning-with","title":"End-to-End Dense Video Captioning with Parallel Decoding","date":"2021-08-17","arxiv_id":"2108.07781","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["ttengwang/pdvc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-dense-video-captioning-with#ran","syntology_url":"https://syntology.ai/paper/2108.07781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07781"}}}},{"paper":"/paper/global-object-proposals-for-improving-multi","slug":"global-object-proposals-for-improving-multi","title":"Global Object Proposals for Improving Multi-Sentence Video Descriptions","date":"2021-07-18","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tsp-temporally-sensitive-pretraining-of-video","slug":"tsp-temporally-sensitive-pretraining-of-video","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","date":"2020-11-23","arxiv_id":"2011.11479","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vlg-net-video-language-graph-matching-network","slug":"vlg-net-video-language-graph-matching-network","title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","date":"2020-11-19","arxiv_id":"2011.10132","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vlg-net-video-language-graph-matching-network#ran","syntology_url":"https://syntology.ai/paper/2011.10132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.10132"}}}},{"paper":"/paper/iperceive-applying-common-sense-reasoning-to-1","slug":"iperceive-applying-common-sense-reasoning-to-1","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering","date":"2020-11-16","arxiv_id":"2011.07735","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/coot-cooperative-hierarchical-transformer-for","slug":"coot-cooperative-hierarchical-transformer-for","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","date":"2020-11-01","arxiv_id":"2011.00597","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["gingsi/coot-videotext"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coot-cooperative-hierarchical-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2011.00597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.00597"}}}},{"paper":"/paper/dense-captioning-events-in-videos-sysu","slug":"dense-captioning-events-in-videos-sysu","title":"Dense-Captioning Events in Videos: SYSU Submission to ActivityNet Challenge 2020","date":"2020-06-21","arxiv_id":"2006.11693","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/team-ruc-aim3-technical-report-at-activitynet","slug":"team-ruc-aim3-technical-report-at-activitynet","title":"Team RUC_AIM3 Technical Report at Activitynet 2020 Task 2: Exploring Sequential Events Detection for Dense Video Captioning","date":"2020-06-14","arxiv_id":"2006.07896","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-better-use-of-audio-visual-cues-dense-video","slug":"a-better-use-of-audio-visual-cues-dense-video","title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer","date":"2020-05-17","arxiv_id":"2005.08271","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["v-iashin/BMT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-better-use-of-audio-visual-cues-dense-video#ran","syntology_url":"https://syntology.ai/paper/2005.08271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08271"}}}},{"paper":"/paper/mart-memory-augmented-recurrent-transformer","slug":"mart-memory-augmented-recurrent-transformer","title":"MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning","date":"2020-05-11","arxiv_id":"2005.05402","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["jayleicn/recurrent-transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mart-memory-augmented-recurrent-transformer#ran","syntology_url":"https://syntology.ai/paper/2005.05402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05402"}}}},{"paper":"/paper/dense-regression-network-for-video-grounding","slug":"dense-regression-network-for-video-grounding","title":"Dense Regression Network for Video Grounding","date":"2020-04-07","arxiv_id":"2004.03545","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modal-dense-video-captioning","slug":"multi-modal-dense-video-captioning","title":"Multi-modal Dense Video Captioning","date":"2020-03-17","arxiv_id":"2003.07758","rows_on_this_dataset":1,"code_links":4,"syntology":null}],"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/dataset/activitynet-captions/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/activitynet-captions/papers/ran/1","json":"/dataset/activitynet-captions/papers/ran/1.json","rows":8}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":8,"samples_harvested":49,"samples_ran":38,"samples_constructed":1,"samples_ran_checked":28,"samples_ran_instrument_failed":10,"samples_unverified":11,"pointer_only_for_licence":12,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":8,"papers_with_a_run_with_no_instrument_failure":7,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"6f5d88dc8f7cbff3e89906a89d4fc27be7f667e760b0277705fe0e75ad5e2be7","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}