{"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/youcook2","name":"YouCook2","full_name":null,"description_markdown":"**YouCook2** is the largest task-oriented, instructional video dataset in the vision community. It contains 2000 long untrimmed videos from 89 cooking recipes; on average, each distinct recipe has 22 videos. The procedure steps for each video are annotated with temporal boundaries and described by imperative English sentences (see the example below). The videos were downloaded from YouTube and are all in the third-person viewpoint. All the videos are unconstrained and can be performed by individual persons at their houses with unfixed cameras. YouCook2 contains rich recipe types and various cooking styles from all over the world.\r\n\r\nSource: [http://youcook2.eecs.umich.edu/](http://youcook2.eecs.umich.edu/)\r\nImage Source: [https://competitions.codalab.org/competitions/20594](https://competitions.codalab.org/competitions/20594)","description_withheld":null,"homepage":"http://youcook2.eecs.umich.edu/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/towards-automatic-learning-of-procedures-from","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","first_author":"Luowei Zhou","url":null},"license":{"name":"Custom","url":"http://youcook2.eecs.umich.edu/download"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Video Retrieval","url":"/task/video-retrieval","datasets_with_task":"/datasets/task/video-retrieval"},{"name":"Action Classification","url":"/task/action-classification","datasets_with_task":"/datasets/task/action-classification"},{"name":"Video Captioning","url":"/task/video-captioning","datasets_with_task":"/datasets/task/video-captioning"},{"name":"Zero-Shot Video Retrieval","url":"/task/zero-shot-video-retrieval","datasets_with_task":"/datasets/task/zero-shot-video-retrieval"},{"name":"Dense Video Captioning","url":"/task/dense-video-captioning","datasets_with_task":"/datasets/task/dense-video-captioning"},{"name":"Zero-shot dense video captioning","url":"/task/zero-shot-dense-video-captioning","datasets_with_task":"/datasets/task/zero-shot-dense-video-captioning"},{"name":"Zero-Shot Video-Audio Retrieval","url":"/task/zero-shot-video-audio-retrieval","datasets_with_task":"/datasets/task/zero-shot-video-audio-retrieval"},{"name":"Long Video Retrieval (Background Removed)","url":"/task/long-video-retrieval-background-removed","datasets_with_task":"/datasets/task/long-video-retrieval-background-removed"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["YouCook2"],"data_loaders":[],"num_papers_in_archive":198,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-retrieval-on-youcook2","task":"Video Retrieval","dataset_variant":"YouCook2","rows":16,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video Median Rank","text-to-video Mean Rank"],"first_row_in_archive_order":{"model":"VAST","paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","metrics":{"text-to-video R@1":"50.4","text-to-video R@10":"80.8","text-to-video R@5":"74.3"},"code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-captioning-on-youcook2","task":"Video Captioning","dataset_variant":"YouCook2","rows":14,"metrics":["BLEU-4","BLEU-3","CIDEr","ROUGE-L","METEOR"],"first_row_in_archive_order":{"model":"VAST","paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","metrics":{"BLEU-4":"18.2","CIDEr":"1.99"},"code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-video-retrieval-on-youcook2","task":"Zero-Shot Video Retrieval","dataset_variant":"YouCook2","rows":9,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video Mean Rank","text-to-video Median Rank"],"first_row_in_archive_order":{"model":"OmniVec2","paper":"/paper/omnivec2-a-novel-transformer-based-network","metrics":{"text-to-video R@1":"26.1","text-to-video R@10":"70.8","text-to-video R@5":"54.1"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/dense-video-captioning-on-youcook2","task":"Dense Video Captioning","dataset_variant":"YouCook2","rows":7,"metrics":["CIDEr","METEOR","SODA","BLEU4","ROUGE-L","F1","Precision","Recall"],"first_row_in_archive_order":{"model":"HiCM²","paper":"/paper/hicm-2-hierarchical-compact-memory-modeling","metrics":{"BLEU4":"6.11","CIDEr":"71.84","F1":"32.51","METEOR":"12.80","Precision":"32.51","Recall":"32.51","SODA":"10.73"},"code_links":[{"title":"ailab-kyunghee/HiCM2-DVC","url":"https://github.com/ailab-kyunghee/HiCM2-DVC"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/long-video-retrieval-background-removed-on","task":"Long Video Retrieval (Background Removed)","dataset_variant":"YouCook2","rows":6,"metrics":["Cap. Avg. R@1","Cap. Avg. R@5","Cap. Avg. R@10","DTW R@1","DTW R@5","DTW R@10","OTAM R@1","OTAM R@5","OTAM R@10"],"first_row_in_archive_order":{"model":"Norton","paper":"/paper/multi-granularity-correspondence-learning-1","metrics":{"Cap. Avg. R@1":"75.5","Cap. Avg. R@10":"97.7","Cap. Avg. R@5":"95.0","DTW R@1":"88.7","DTW R@10":"99.5","DTW R@5":"98.8","OTAM R@1":"88.9","OTAM R@10":"99.5","OTAM R@5":"98.4"},"code_links":[{"title":"XLearning-SCU/2024-ICLR-Norton","url":"https://github.com/XLearning-SCU/2024-ICLR-Norton"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-classification-on-youcook2","task":"Action Classification","dataset_variant":"YouCook2","rows":1,"metrics":["Object Top 5 Accuracy","Object Top-1 Accuracy","Verb Top-1 Accuracy","Verb Top-5 Accuracy"],"first_row_in_archive_order":{"model":"VideoBERT (cross modal)","paper":"/paper/videobert-a-joint-model-for-video-and","metrics":{"Object Top 5 Accuracy":"33.7","Object Top-1 Accuracy":"13.1","Verb Top-1 Accuracy":"3.2","Verb Top-5 Accuracy":"43.3"},"code_links":[{"title":"ammesatyajit/VideoBERT","url":"https://github.com/ammesatyajit/VideoBERT"},{"title":"MDSKUL/MasterProject","url":"https://github.com/MDSKUL/MasterProject"},{"title":"parkervg/allrecipes-bert","url":"https://github.com/parkervg/allrecipes-bert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-dense-video-captioning-on-youcook2","task":"Zero-shot dense video captioning","dataset_variant":"YouCook2","rows":1,"metrics":["CIDEr","METEOR","SODA"],"first_row_in_archive_order":{"model":"Vid2Seq (HowTo100M+VidChapters-7M PT)","paper":null,"metrics":{"CIDEr":"13.3","METEOR":"3.4","SODA":"3.9"},"code_links":[]},"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":33,"of":33,"counts":{"papers_with_a_benchmark_row":33,"with_a_code_link":25,"where_syntology_ran_a_sample":16,"not_listed_spam_title":0,"listed":33,"listed_where_code_ran":16,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":5,"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/hicm-2-hierarchical-compact-memory-modeling","slug":"hicm-2-hierarchical-compact-memory-modeling","title":"HiCM$^2$: Hierarchical Compact Memory Modeling for Dense Video Captioning","date":"2024-12-19","arxiv_id":"2412.14585","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/ma-lmm-memory-augmented-large-multimodal","slug":"ma-lmm-memory-augmented-large-multimodal","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","date":"2024-04-08","arxiv_id":"2404.05726","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["boheumd/MA-LMM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ma-lmm-memory-augmented-large-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.05726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05726"}}}},{"paper":"/paper/multi-granularity-correspondence-learning-1","slug":"multi-granularity-correspondence-learning-1","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","date":"2024-01-30","arxiv_id":"2401.16702","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-granularity-correspondence-learning-1#ran","syntology_url":"https://syntology.ai/paper/2401.16702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16702"}}}},{"paper":"/paper/omnivec2-a-novel-transformer-based-network","slug":"omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/omnivec-learning-robust-representations-with","slug":"omnivec-learning-robust-representations-with","title":"OmniVec: Learning robust representations with cross modal sharing","date":"2023-11-07","arxiv_id":"2311.05709","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/howtocaption-prompting-llms-to-transform","slug":"howtocaption-prompting-llms-to-transform","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","date":"2023-10-07","arxiv_id":"2310.04900","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":5,"official":{"repos":["ninatu/howtocaption"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/howtocaption-prompting-llms-to-transform#ran","syntology_url":"https://syntology.ai/paper/2310.04900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04900"}}}},{"paper":"/paper/cosa-concatenated-sample-pretrained-vision","slug":"cosa-concatenated-sample-pretrained-vision","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","date":"2023-06-15","arxiv_id":"2306.09085","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":42,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":25,"samples_ran_instrument_failed":10,"samples_unverified":7,"pointer_only_for_licence":8,"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}}}},{"paper":"/paper/meltr-meta-loss-transformer-for-learning-to","slug":"meltr-meta-loss-transformer-for-learning-to","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","date":"2023-03-23","arxiv_id":"2303.13009","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["mlvlab/MELTR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/meltr-meta-loss-transformer-for-learning-to#ran","syntology_url":"https://syntology.ai/paper/2303.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13009"}}}},{"paper":"/paper/text-with-knowledge-graph-augmented","slug":"text-with-knowledge-graph-augmented","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","date":"2023-03-22","arxiv_id":"2303.12423","rows_on_this_dataset":1,"code_links":0,"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":1,"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/tempclr-temporal-alignment-representation","slug":"tempclr-temporal-alignment-representation","title":"TempCLR: Temporal Alignment Representation with Contrastive Learning","date":"2022-12-28","arxiv_id":"2212.13738","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["yyuncong/tempclr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tempclr-temporal-alignment-representation#ran","syntology_url":"https://syntology.ai/paper/2212.13738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13738"}}}},{"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":3,"code_links":0,"syntology":null},{"paper":"/paper/omnivl-one-foundation-model-for-image","slug":"omnivl-one-foundation-model-for-image","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","date":"2022-09-15","arxiv_id":"2209.07526","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rome-role-aware-mixture-of-expert-transformer","slug":"rome-role-aware-mixture-of-expert-transformer","title":"RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval","date":"2022-06-26","arxiv_id":"2206.12845","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semantic-role-aware-correlation-transformer","slug":"semantic-role-aware-correlation-transformer","title":"Semantic Role Aware Correlation Transformer for Text to Video Retrieval","date":"2022-06-26","arxiv_id":"2206.12849","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mdmmt-2-multidomain-multimodal-transformer","slug":"mdmmt-2-multidomain-multimodal-transformer","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","date":"2022-03-14","arxiv_id":"2203.07086","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/videoclip-contrastive-pre-training-for-zero","slug":"videoclip-contrastive-pre-training-for-zero","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","date":"2021-09-28","arxiv_id":"2109.14084","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/taco-token-aware-cascade-contrastive-learning","slug":"taco-token-aware-cascade-contrastive-learning","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","date":"2021-08-23","arxiv_id":"2108.09980","rows_on_this_dataset":2,"code_links":0,"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/vlm-task-agnostic-video-language-model-pre","slug":"vlm-task-agnostic-video-language-model-pre","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","date":"2021-05-20","arxiv_id":"2105.09996","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multimodal-clustering-networks-for-self","slug":"multimodal-clustering-networks-for-self","title":"Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos","date":"2021-04-26","arxiv_id":"2104.12671","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":1,"official":{"repos":["brian7685/Multimodal-Clustering-Network"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multimodal-clustering-networks-for-self#ran","syntology_url":"https://syntology.ai/paper/2104.12671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12671"}}}},{"paper":"/paper/vatt-transformers-for-multimodal-self","slug":"vatt-transformers-for-multimodal-self","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","date":"2021-04-22","arxiv_id":"2104.11178","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":4,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":8,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vatt-transformers-for-multimodal-self#ran","syntology_url":"https://syntology.ai/paper/2104.11178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11178"}}}},{"paper":"/paper/multimodal-pretraining-for-dense-video","slug":"multimodal-pretraining-for-dense-video","title":"Multimodal Pretraining for Dense Video Captioning","date":"2020-11-10","arxiv_id":"2011.11760","rows_on_this_dataset":2,"code_links":1,"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":2,"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/univilm-a-unified-video-and-language-pre","slug":"univilm-a-unified-video-and-language-pre","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","date":"2020-02-15","arxiv_id":"2002.06353","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["microsoft/UniVL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/univilm-a-unified-video-and-language-pre#ran","syntology_url":"https://syntology.ai/paper/2002.06353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06353"}}}},{"paper":"/paper/end-to-end-learning-of-visual-representations","slug":"end-to-end-learning-of-visual-representations","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","date":"2019-12-13","arxiv_id":"1912.06430","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["antoine77340/MIL-NCE_HowTo100M"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-learning-of-visual-representations#ran","syntology_url":"https://syntology.ai/paper/1912.06430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.06430"}}}},{"paper":"/paper/howto100m-learning-a-text-video-embedding-by","slug":"howto100m-learning-a-text-video-embedding-by","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","date":"2019-06-07","arxiv_id":"1906.03327","rows_on_this_dataset":2,"code_links":4,"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":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/howto100m-learning-a-text-video-embedding-by#ran","syntology_url":"https://syntology.ai/paper/1906.03327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03327"}}}},{"paper":"/paper/videobert-a-joint-model-for-video-and","slug":"videobert-a-joint-model-for-video-and","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","date":"2019-04-03","arxiv_id":"1904.01766","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videobert-a-joint-model-for-video-and#ran","syntology_url":"https://syntology.ai/paper/1904.01766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01766"}}}},{"paper":"/paper/end-to-end-dense-video-captioning-with-masked","slug":"end-to-end-dense-video-captioning-with-masked","title":"End-to-End Dense Video Captioning with Masked Transformer","date":"2018-04-03","arxiv_id":"1804.00819","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/associating-neural-word-embeddings-with-deep","slug":"associating-neural-word-embeddings-with-deep","title":"Associating Neural Word Embeddings With Deep Image Representations Using Fisher Vectors","date":"2015-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/hicm-2-hierarchical-compact-memory-modeling","slug":"hicm-2-hierarchical-compact-memory-modeling","title":"HiCM$^2$: Hierarchical Compact Memory Modeling for Dense Video Captioning","date":"2024-12-19","arxiv_id":"2412.14585","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/ma-lmm-memory-augmented-large-multimodal","slug":"ma-lmm-memory-augmented-large-multimodal","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","date":"2024-04-08","arxiv_id":"2404.05726","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["boheumd/MA-LMM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ma-lmm-memory-augmented-large-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.05726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05726"}}}},{"paper":"/paper/multi-granularity-correspondence-learning-1","slug":"multi-granularity-correspondence-learning-1","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","date":"2024-01-30","arxiv_id":"2401.16702","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-granularity-correspondence-learning-1#ran","syntology_url":"https://syntology.ai/paper/2401.16702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16702"}}}},{"paper":"/paper/omnivec2-a-novel-transformer-based-network","slug":"omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/omnivec-learning-robust-representations-with","slug":"omnivec-learning-robust-representations-with","title":"OmniVec: Learning robust representations with cross modal sharing","date":"2023-11-07","arxiv_id":"2311.05709","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/howtocaption-prompting-llms-to-transform","slug":"howtocaption-prompting-llms-to-transform","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","date":"2023-10-07","arxiv_id":"2310.04900","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":5,"official":{"repos":["ninatu/howtocaption"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/howtocaption-prompting-llms-to-transform#ran","syntology_url":"https://syntology.ai/paper/2310.04900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04900"}}}},{"paper":"/paper/cosa-concatenated-sample-pretrained-vision","slug":"cosa-concatenated-sample-pretrained-vision","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","date":"2023-06-15","arxiv_id":"2306.09085","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":42,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":25,"samples_ran_instrument_failed":10,"samples_unverified":7,"pointer_only_for_licence":8,"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}}}},{"paper":"/paper/meltr-meta-loss-transformer-for-learning-to","slug":"meltr-meta-loss-transformer-for-learning-to","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","date":"2023-03-23","arxiv_id":"2303.13009","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["mlvlab/MELTR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/meltr-meta-loss-transformer-for-learning-to#ran","syntology_url":"https://syntology.ai/paper/2303.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13009"}}}},{"paper":"/paper/text-with-knowledge-graph-augmented","slug":"text-with-knowledge-graph-augmented","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","date":"2023-03-22","arxiv_id":"2303.12423","rows_on_this_dataset":1,"code_links":0,"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":1,"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/tempclr-temporal-alignment-representation","slug":"tempclr-temporal-alignment-representation","title":"TempCLR: Temporal Alignment Representation with Contrastive Learning","date":"2022-12-28","arxiv_id":"2212.13738","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["yyuncong/tempclr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tempclr-temporal-alignment-representation#ran","syntology_url":"https://syntology.ai/paper/2212.13738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13738"}}}},{"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":3,"code_links":0,"syntology":null},{"paper":"/paper/omnivl-one-foundation-model-for-image","slug":"omnivl-one-foundation-model-for-image","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","date":"2022-09-15","arxiv_id":"2209.07526","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rome-role-aware-mixture-of-expert-transformer","slug":"rome-role-aware-mixture-of-expert-transformer","title":"RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval","date":"2022-06-26","arxiv_id":"2206.12845","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semantic-role-aware-correlation-transformer","slug":"semantic-role-aware-correlation-transformer","title":"Semantic Role Aware Correlation Transformer for Text to Video Retrieval","date":"2022-06-26","arxiv_id":"2206.12849","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mdmmt-2-multidomain-multimodal-transformer","slug":"mdmmt-2-multidomain-multimodal-transformer","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","date":"2022-03-14","arxiv_id":"2203.07086","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/videoclip-contrastive-pre-training-for-zero","slug":"videoclip-contrastive-pre-training-for-zero","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","date":"2021-09-28","arxiv_id":"2109.14084","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/taco-token-aware-cascade-contrastive-learning","slug":"taco-token-aware-cascade-contrastive-learning","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","date":"2021-08-23","arxiv_id":"2108.09980","rows_on_this_dataset":2,"code_links":0,"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/vlm-task-agnostic-video-language-model-pre","slug":"vlm-task-agnostic-video-language-model-pre","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","date":"2021-05-20","arxiv_id":"2105.09996","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multimodal-clustering-networks-for-self","slug":"multimodal-clustering-networks-for-self","title":"Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos","date":"2021-04-26","arxiv_id":"2104.12671","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":1,"official":{"repos":["brian7685/Multimodal-Clustering-Network"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multimodal-clustering-networks-for-self#ran","syntology_url":"https://syntology.ai/paper/2104.12671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12671"}}}},{"paper":"/paper/vatt-transformers-for-multimodal-self","slug":"vatt-transformers-for-multimodal-self","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","date":"2021-04-22","arxiv_id":"2104.11178","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":4,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":8,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vatt-transformers-for-multimodal-self#ran","syntology_url":"https://syntology.ai/paper/2104.11178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11178"}}}},{"paper":"/paper/multimodal-pretraining-for-dense-video","slug":"multimodal-pretraining-for-dense-video","title":"Multimodal Pretraining for Dense Video Captioning","date":"2020-11-10","arxiv_id":"2011.11760","rows_on_this_dataset":2,"code_links":1,"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":2,"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/univilm-a-unified-video-and-language-pre","slug":"univilm-a-unified-video-and-language-pre","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","date":"2020-02-15","arxiv_id":"2002.06353","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["microsoft/UniVL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/univilm-a-unified-video-and-language-pre#ran","syntology_url":"https://syntology.ai/paper/2002.06353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06353"}}}},{"paper":"/paper/end-to-end-learning-of-visual-representations","slug":"end-to-end-learning-of-visual-representations","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","date":"2019-12-13","arxiv_id":"1912.06430","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["antoine77340/MIL-NCE_HowTo100M"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-learning-of-visual-representations#ran","syntology_url":"https://syntology.ai/paper/1912.06430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.06430"}}}},{"paper":"/paper/howto100m-learning-a-text-video-embedding-by","slug":"howto100m-learning-a-text-video-embedding-by","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","date":"2019-06-07","arxiv_id":"1906.03327","rows_on_this_dataset":2,"code_links":4,"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":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/howto100m-learning-a-text-video-embedding-by#ran","syntology_url":"https://syntology.ai/paper/1906.03327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03327"}}}},{"paper":"/paper/videobert-a-joint-model-for-video-and","slug":"videobert-a-joint-model-for-video-and","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","date":"2019-04-03","arxiv_id":"1904.01766","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videobert-a-joint-model-for-video-and#ran","syntology_url":"https://syntology.ai/paper/1904.01766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01766"}}}},{"paper":"/paper/end-to-end-dense-video-captioning-with-masked","slug":"end-to-end-dense-video-captioning-with-masked","title":"End-to-End Dense Video Captioning with Masked Transformer","date":"2018-04-03","arxiv_id":"1804.00819","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/associating-neural-word-embeddings-with-deep","slug":"associating-neural-word-embeddings-with-deep","title":"Associating Neural Word Embeddings With Deep Image Representations Using Fisher Vectors","date":"2015-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":16,"papers_where_code_ran_first_page":"/dataset/youcook2/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/youcook2/papers/ran/1","json":"/dataset/youcook2/papers/ran/1.json","rows":16}],"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":16,"samples_harvested":113,"samples_ran":87,"samples_constructed":11,"samples_ran_checked":59,"samples_ran_instrument_failed":28,"samples_unverified":26,"pointer_only_for_licence":28,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":16,"papers_with_a_run_with_no_instrument_failure":11,"papers_where_every_run_was_an_instrument_failure":5,"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":2,"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/dense-video-captioning-on-youcook2","since_archive":"/sota/dense-video-captioning-on-youcook2#since-judged","papers_judged":2,"placed":0}]},"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":"b3ee58523ad5349436b3d3fa5732681af5b6d4531d632d0ef1db9fac111ae1d9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}