{"url":"/sota/video-captioning-on-youcook2","task":{"name":"Video Captioning","url":"/task/video-captioning","note":null},"dataset":{"name":"YouCook2","url":"/dataset/youcook2"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Video Captioning** is a task of automatic captioning a video by understanding the action and event in the video which can help in the retrieval of the video efficiently through text.\r\n\r\n\r\n<span class=\"description-source\">Source: [NITS-VC System for VATEX Video Captioning Challenge 2020 ](https://arxiv.org/abs/2006.04058)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["BLEU-4","BLEU-3","CIDEr","ROUGE-L","METEOR"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"BLEU-4":"higher","BLEU-3":"higher","CIDEr":null,"ROUGE-L":"higher","METEOR":null}},"counts":{"rows":14,"rows_with_code":11,"rows_with_paper_page":14,"rows_dated":14,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"VAST","metrics":{"BLEU-4":"18.2","CIDEr":"1.99"},"uses_additional_data":true,"paper_date":"2023-05-29","paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","paper_url":"https://arxiv.org/abs/2305.18500v2","paper_title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","code":"https://github.com/TXH-mercury/VALOR","n_code_links":2,"syntology":{"n_ran":15,"n_unverified":27,"n_samples":42,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"UniVL + MELTR","metrics":{"BLEU-3":"24.12","BLEU-4":"17.92","CIDEr":"1.90","METEOR":"22.56","ROUGE-L":"47.04"},"uses_additional_data":false,"paper_date":"2023-03-23","paper":"/paper/meltr-meta-loss-transformer-for-learning-to","paper_url":"https://arxiv.org/abs/2303.13009v1","paper_title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","code":"https://github.com/mlvlab/MELTR","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"UniVL","metrics":{"BLEU-3":"23.87","BLEU-4":"17.35","CIDEr":"1.81","METEOR":"22.35","ROUGE-L":"46.52"},"uses_additional_data":true,"paper_date":"2020-02-15","paper":"/paper/univilm-a-unified-video-and-language-pre","paper_url":"https://arxiv.org/abs/2002.06353v3","paper_title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","code":"https://github.com/microsoft/UniVL","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":4,"model":"VideoCoCa","metrics":{"BLEU-4":"14.2","CIDEr":"1.28","ROUGE-L":"37.7"},"uses_additional_data":true,"paper_date":"2022-12-09","paper":"/paper/video-text-modeling-with-zero-shot-transfer","paper_url":"https://arxiv.org/abs/2212.04979v3","paper_title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"VLM","metrics":{"BLEU-3":"17.78","BLEU-4":"12.27","CIDEr":"1.3869","METEOR":"18.22","ROUGE-L":"41.51"},"uses_additional_data":true,"paper_date":"2021-05-20","paper":"/paper/vlm-task-agnostic-video-language-model-pre","paper_url":"https://arxiv.org/abs/2105.09996v3","paper_title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","code":"https://github.com/pytorch/fairseq","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"E2vidD6-MASSvid-BiD","metrics":{"BLEU-4":"12.04","CIDEr":"1.22","METEOR":"18.32","ROUGE-L":"39.03"},"uses_additional_data":true,"paper_date":"2020-11-10","paper":"/paper/multimodal-pretraining-for-dense-video","paper_url":"https://arxiv.org/abs/2011.11760v1","paper_title":"Multimodal Pretraining for Dense Video Captioning","code":"https://github.com/google-research-datasets/Video-Timeline-Tags-ViTT","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"TextKG","metrics":{"BLEU-4":"11.7","CIDEr":"1.33","METEOR":"14.8","ROUGE-L":"40.2"},"uses_additional_data":false,"paper_date":"2023-03-22","paper":"/paper/text-with-knowledge-graph-augmented","paper_url":"https://arxiv.org/abs/2303.12423v2","paper_title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"COOT","metrics":{"BLEU-3":"17.97","BLEU-4":"11.30","CIDEr":"0.57","METEOR":"19.85","ROUGE-L":"37.94"},"uses_additional_data":true,"paper_date":"2020-11-01","paper":"/paper/coot-cooperative-hierarchical-transformer-for","paper_url":"https://arxiv.org/abs/2011.00597v1","paper_title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","code":"https://github.com/gingsi/coot-videotext","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"COSA","metrics":{"BLEU-4":"10.1","CIDEr":"1.31"},"uses_additional_data":true,"paper_date":"2023-06-15","paper":"/paper/cosa-concatenated-sample-pretrained-vision","paper_url":"https://arxiv.org/abs/2306.09085v1","paper_title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","code":"https://github.com/txh-mercury/cosa","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"HowToCaption","metrics":{"BLEU-4":"8.8","CIDEr":"116.4","METEOR":"15.9","ROUGE-L":"37.3"},"uses_additional_data":false,"paper_date":"2023-10-07","paper":"/paper/howtocaption-prompting-llms-to-transform","paper_url":"https://arxiv.org/abs/2310.04900v2","paper_title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","code":"https://github.com/ninatu/howtocaption","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":11,"model":"OmniVL","metrics":{"BLEU-3":"12.87","BLEU-4":"8.72","CIDEr":"1.16","METEOR":"14.83","ROUGE-L":"36.09"},"uses_additional_data":false,"paper_date":"2022-09-15","paper":"/paper/omnivl-one-foundation-model-for-image","paper_url":"https://arxiv.org/abs/2209.07526v2","paper_title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"Zhou","metrics":{"BLEU-3":"7.53","BLEU-4":"4.38","CIDEr":"0.38","METEOR":"11.55","ROUGE-L":"27.44"},"uses_additional_data":false,"paper_date":"2018-04-03","paper":"/paper/end-to-end-dense-video-captioning-with-masked","paper_url":"http://arxiv.org/abs/1804.00819v1","paper_title":"End-to-End Dense Video Captioning with Masked Transformer","code":"https://github.com/salesforce/densecap","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"VideoBERT + S3D","metrics":{"BLEU-3":"7.59","BLEU-4":"4.33","CIDEr":"0.55","METEOR":"11.94","ROUGE-L":"28.80"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/videobert-a-joint-model-for-video-and","paper_url":"https://arxiv.org/abs/1904.01766v2","paper_title":"VideoBERT: A Joint Model for Video and Language Representation Learning","code":"https://github.com/ammesatyajit/VideoBERT","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"MA-LMM","metrics":{"CIDEr":"1.31","METEOR":"17.6"},"uses_additional_data":false,"paper_date":"2024-04-08","paper":"/paper/ma-lmm-memory-augmented-large-multimodal","paper_url":"https://arxiv.org/abs/2404.05726v2","paper_title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","code":"https://github.com/boheumd/MA-LMM","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":7,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":28,"n_unverified":40,"n_samples":68,"n_pointer_only_licence":6,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":28,"n_unverified":40,"n_samples":68,"n_pointer_only_licence":6,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}