{"url":"/sota/visual-question-answering-on-msrvtt-qa-1","task":{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","note":null},"dataset":{"name":"MSRVTT-QA","url":"/dataset/msrvtt-qa"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"**Visual Question Answering (VQA)** is a task in computer vision that involves answering questions about an image. The goal of VQA is to teach machines to understand the content of an image and answer questions about it in natural language.\r\n\r\nImage Source: [visualqa.org](https://visualqa.org/)","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":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":34,"rows_with_code":27,"rows_with_paper_page":34,"rows_dated":34,"rows_using_additional_data":18},"rows":[{"rank_in_archive_order":1,"model":"VLAB","metrics":{"Accuracy":"0.496"},"uses_additional_data":true,"paper_date":"2023-05-22","paper":"/paper/vlab-enhancing-video-language-pre-training-by","paper_url":"https://arxiv.org/abs/2305.13167v1","paper_title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"MaMMUT","metrics":{"Accuracy":"0.495"},"uses_additional_data":true,"paper_date":"2023-03-29","paper":"/paper/mammut-a-simple-architecture-for-joint","paper_url":"https://arxiv.org/abs/2303.16839v3","paper_title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","code":"https://github.com/lucidrains/mammut-pytorch","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"mPLUG-2","metrics":{"Accuracy":"0.480"},"uses_additional_data":true,"paper_date":"2023-02-01","paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","paper_url":"https://arxiv.org/abs/2302.00402v1","paper_title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","code":"https://github.com/modelscope/modelscope","n_code_links":4,"syntology":{"n_ran":9,"n_unverified":10,"n_samples":19,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"MuLTI","metrics":{"Accuracy":"0.478"},"uses_additional_data":true,"paper_date":"2023-03-10","paper":"/paper/multi-efficient-video-and-language","paper_url":"https://arxiv.org/abs/2303.05707v2","paper_title":"MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"Flamingo","metrics":{"Accuracy":"0.474"},"uses_additional_data":true,"paper_date":"2022-04-29","paper":"/paper/flamingo-a-visual-language-model-for-few-shot-1","paper_url":"https://arxiv.org/abs/2204.14198v2","paper_title":"Flamingo: a Visual Language Model for Few-Shot Learning","code":"https://github.com/mlfoundations/open_flamingo","n_code_links":5,"syntology":{"n_ran":18,"n_unverified":6,"n_samples":24,"n_pointer_only_licence":7}},{"rank_in_archive_order":6,"model":"InternVideo","metrics":{"Accuracy":"0.471"},"uses_additional_data":true,"paper_date":"2022-12-06","paper":"/paper/internvideo-general-video-foundation-models","paper_url":"https://arxiv.org/abs/2212.03191v2","paper_title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"UMT-L (ViT-L/16)","metrics":{"Accuracy":"0.471"},"uses_additional_data":true,"paper_date":"2023-03-28","paper":"/paper/unmasked-teacher-towards-training-efficient","paper_url":"https://arxiv.org/abs/2303.16058v2","paper_title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","code":"https://github.com/opengvlab/unmasked_teacher","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"FrozenBiLM+","metrics":{"Accuracy":"0.470"},"uses_additional_data":false,"paper_date":"2023-08-18","paper":"/paper/open-vocabulary-video-question-answering-a","paper_url":"https://arxiv.org/abs/2308.09363v1","paper_title":"Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models","code":"https://github.com/mlvlab/ovqa","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":9,"model":"vid-TLDR (UMT-L)","metrics":{"Accuracy":"0.470"},"uses_additional_data":true,"paper_date":"2024-03-20","paper":"/paper/vid-tldr-training-free-token-merging-for","paper_url":"https://arxiv.org/abs/2403.13347v2","paper_title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","code":"https://github.com/mlvlab/vid-tldr","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"VideoCoCa","metrics":{"Accuracy":"0.463"},"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":11,"model":"HBI","metrics":{"Accuracy":"0.462"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/video-text-as-game-players-hierarchical","paper_url":"https://arxiv.org/abs/2303.14369v1","paper_title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","code":"https://github.com/jpthu17/emcl","n_code_links":4,"syntology":{"n_ran":11,"n_unverified":5,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"HiTeA","metrics":{"Accuracy":"0.459"},"uses_additional_data":true,"paper_date":"2022-12-30","paper":"/paper/hitea-hierarchical-temporal-aware-video","paper_url":"https://arxiv.org/abs/2212.14546v1","paper_title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"EMCL-Net","metrics":{"Accuracy":"0.458"},"uses_additional_data":false,"paper_date":"2022-11-21","paper":"/paper/expectation-maximization-contrastive-learning","paper_url":"https://arxiv.org/abs/2211.11427v1","paper_title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","code":"https://github.com/jpthu17/emcl","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"Co-Tokenization","metrics":{"Accuracy":".457"},"uses_additional_data":true,"paper_date":"2022-08-01","paper":"/paper/video-question-answering-with-iterative-video","paper_url":"https://arxiv.org/abs/2208.00934v1","paper_title":"Video Question Answering with Iterative Video-Text Co-Tokenization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"X2-VLM (large)","metrics":{"Accuracy":"0.455"},"uses_additional_data":true,"paper_date":"2022-11-22","paper":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","paper_url":"https://arxiv.org/abs/2211.12402v2","paper_title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","code":"https://github.com/zengyan-97/x-vlm","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":16,"model":"X2-VLM (base)","metrics":{"Accuracy":"0.45"},"uses_additional_data":true,"paper_date":"2022-11-22","paper":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","paper_url":"https://arxiv.org/abs/2211.12402v2","paper_title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","code":"https://github.com/zengyan-97/x-vlm","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":17,"model":"All-in-one-B","metrics":{"Accuracy":"0.443"},"uses_additional_data":true,"paper_date":"2022-03-14","paper":"/paper/all-in-one-exploring-unified-video-language","paper_url":"https://arxiv.org/abs/2203.07303v1","paper_title":"All in One: Exploring Unified Video-Language Pre-training","code":"https://github.com/showlab/all-in-one","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"OmniVL","metrics":{"Accuracy":"0.441"},"uses_additional_data":true,"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":19,"model":"Clover","metrics":{"Accuracy":"0.441"},"uses_additional_data":true,"paper_date":"2022-07-16","paper":"/paper/clover-towards-a-unified-video-language","paper_url":"https://arxiv.org/abs/2207.07885v3","paper_title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","code":"https://github.com/leeyn-43/clover","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"AIO+MIF","metrics":{"Accuracy":"0.440"},"uses_additional_data":false,"paper_date":"2023-07-09","paper":"/paper/sas-video-qa-self-adaptive-sampling-for","paper_url":"https://arxiv.org/abs/2307.04192v4","paper_title":"Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models","code":"https://github.com/declare-lab/sealing","n_code_links":2,"syntology":null},{"rank_in_archive_order":21,"model":"AIO+MDF","metrics":{"Accuracy":"0.438"},"uses_additional_data":false,"paper_date":"2023-07-09","paper":"/paper/sas-video-qa-self-adaptive-sampling-for","paper_url":"https://arxiv.org/abs/2307.04192v4","paper_title":"Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models","code":"https://github.com/declare-lab/sealing","n_code_links":2,"syntology":null},{"rank_in_archive_order":22,"model":"GIT+MDF","metrics":{"Accuracy":"0.423"},"uses_additional_data":false,"paper_date":"2023-07-09","paper":"/paper/sas-video-qa-self-adaptive-sampling-for","paper_url":"https://arxiv.org/abs/2307.04192v4","paper_title":"Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models","code":"https://github.com/declare-lab/sealing","n_code_links":2,"syntology":null},{"rank_in_archive_order":23,"model":"ALPRO","metrics":{"Accuracy":"0.421"},"uses_additional_data":true,"paper_date":"2021-12-17","paper":"/paper/align-and-prompt-video-and-language-pre","paper_url":"https://arxiv.org/abs/2112.09583v2","paper_title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","code":"https://github.com/salesforce/alpro","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"LRCE","metrics":{"Accuracy":"0.42"},"uses_additional_data":false,"paper_date":"2023-06-30","paper":"/paper/lightweight-recurrent-cross-modal-encoder-for","paper_url":"https://www.sciencedirect.com/science/article/pii/S0950705123005233","paper_title":"Lightweight Recurrent Cross-modal Encoder for Video Question Answering","code":"https://github.com/Sejong-VLI/VQA-LRCE-KBS-2023","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"JustAsk+","metrics":{"Accuracy":"0.418"},"uses_additional_data":false,"paper_date":"2023-08-18","paper":"/paper/open-vocabulary-video-question-answering-a","paper_url":"https://arxiv.org/abs/2308.09363v1","paper_title":"Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models","code":"https://github.com/mlvlab/ovqa","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":26,"model":"All-in-one+","metrics":{"Accuracy":"0.395"},"uses_additional_data":false,"paper_date":"2023-08-18","paper":"/paper/open-vocabulary-video-question-answering-a","paper_url":"https://arxiv.org/abs/2308.09363v1","paper_title":"Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models","code":"https://github.com/mlvlab/ovqa","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":27,"model":"CLIPBERT","metrics":{"Accuracy":"0.374"},"uses_additional_data":true,"paper_date":"2021-02-11","paper":"/paper/less-is-more-clipbert-for-video-and-language","paper_url":"https://arxiv.org/abs/2102.06183v1","paper_title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","code":"https://github.com/jayleicn/ClipBERT","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"HCRN","metrics":{"Accuracy":"0.356"},"uses_additional_data":false,"paper_date":"2020-02-25","paper":"/paper/hierarchical-conditional-relation-networks","paper_url":"https://arxiv.org/abs/2002.10698v3","paper_title":"Hierarchical Conditional Relation Networks for Video Question Answering","code":"https://github.com/thaolmk54/hcrn-videoqa","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"DualVGR","metrics":{"Accuracy":"0.355"},"uses_additional_data":false,"paper_date":"2021-07-10","paper":"/paper/dualvgr-a-dual-visual-graph-reasoning-unit","paper_url":"https://arxiv.org/abs/2107.04768v1","paper_title":"DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering","code":"https://github.com/MM-IR/DualVGR-VideoQA","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"HMEMA","metrics":{"Accuracy":"0.33"},"uses_additional_data":false,"paper_date":"2019-04-08","paper":"/paper/heterogeneous-memory-enhanced-multimodal","paper_url":"http://arxiv.org/abs/1904.04357v1","paper_title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering","code":"https://github.com/fanchenyou/HME-VideoQA","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"Co-Mem","metrics":{"Accuracy":"0.32"},"uses_additional_data":false,"paper_date":"2018-03-29","paper":"/paper/motion-appearance-co-memory-networks-for","paper_url":"http://arxiv.org/abs/1803.10906v1","paper_title":"Motion-Appearance Co-Memory Networks for Video Question Answering","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":32,"model":"Flamingo (32-shot)","metrics":{"Accuracy":"0.310"},"uses_additional_data":false,"paper_date":"2022-04-29","paper":"/paper/flamingo-a-visual-language-model-for-few-shot-1","paper_url":"https://arxiv.org/abs/2204.14198v2","paper_title":"Flamingo: a Visual Language Model for Few-Shot Learning","code":"https://github.com/mlfoundations/open_flamingo","n_code_links":5,"syntology":{"n_ran":18,"n_unverified":6,"n_samples":24,"n_pointer_only_licence":7}},{"rank_in_archive_order":33,"model":"ST-VQA","metrics":{"Accuracy":"0.309"},"uses_additional_data":false,"paper_date":"2017-04-14","paper":"/paper/tgif-qa-toward-spatio-temporal-reasoning-in","paper_url":"http://arxiv.org/abs/1704.04497v3","paper_title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","code":"https://github.com/ahjeongseo/MASN-pytorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":34,"model":"Flamingo (0-shot)","metrics":{"Accuracy":"0.174"},"uses_additional_data":false,"paper_date":"2022-04-29","paper":"/paper/flamingo-a-visual-language-model-for-few-shot-1","paper_url":"https://arxiv.org/abs/2204.14198v2","paper_title":"Flamingo: a Visual Language Model for Few-Shot Learning","code":"https://github.com/mlfoundations/open_flamingo","n_code_links":5,"syntology":{"n_ran":18,"n_unverified":6,"n_samples":24,"n_pointer_only_licence":7}}],"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 6,795 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":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"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":16,"rows_with_any_sample_ran":15,"distinct_papers_with_graph_line":11,"distinct_papers_with_any_sample_ran":10,"samples_over_distinct_papers":{"n_ran":58,"n_unverified":40,"n_samples":98,"n_pointer_only_licence":21,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":102,"n_unverified":66,"n_samples":168,"n_pointer_only_licence":57,"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"}}}