{"url":"/sota/video-quality-assessment-on-msu-video-quality","task":{"name":"Video Quality Assessment","url":"/task/video-quality-assessment","note":null},"dataset":{"name":"MSU NR VQA Database","url":"/dataset/msu-video-quality-metrics-benchmark"},"category":"Computer Vision","categories":["Computer Vision","Time Series"],"category_note":null,"description":"Video Quality Assessment is a computer vision task aiming to mimic video-based human subjective perception. The goal is to produce a mos score, where higher score indicates better perceptual quality. Some well-known benchmarks for this task are KoNViD-1k, LIVE-VQC, YouTube-UGC and LSVQ.  SROCC/PLCC/RMSE are usually used to evaluate the performance of different models.","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":["SRCC","PLCC","KLCC","Type"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"SRCC":null,"PLCC":null,"KLCC":null,"Type":null}},"counts":{"rows":21,"rows_with_code":19,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MDTVSFA","metrics":{"KLCC":"0.7883","PLCC":"0.9431","SRCC":"0.9289","Type":"NR"},"uses_additional_data":false,"paper_date":"2020-11-09","paper":"/paper/unified-quality-assessment-of-in-the-wild","paper_url":"https://arxiv.org/abs/2011.04263v2","paper_title":"Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training","code":"https://github.com/lidq92/MDTVSFA","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DBCNN","metrics":{"KLCC":"0.7750","PLCC":"0.9222","SRCC":"0.9220","Type":"NR"},"uses_additional_data":false,"paper_date":"2019-07-05","paper":"/paper/blind-image-quality-assessment-using-a-deep","paper_url":"https://arxiv.org/abs/1907.02665v1","paper_title":"Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network","code":"https://github.com/zwx8981/DBCNN-PyTorch","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"UNIQUE","metrics":{"KLCC":"0.7648","PLCC":"0.9238","SRCC":"0.9148","Type":"NR"},"uses_additional_data":false,"paper_date":"2018-10-15","paper":"/paper/unique-unsupervised-image-quality-estimation","paper_url":"http://arxiv.org/abs/1810.06631v2","paper_title":"UNIQUE: Unsupervised Image Quality Estimation","code":"https://github.com/olivesgatech/UNIQUE-Unsupervised-Image-Quality-Estimation","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"LI","metrics":{"KLCC":"0.7640","PLCC":"0.9270","SRCC":"0.9131","Type":"NR"},"uses_additional_data":false,"paper_date":"2021-08-19","paper":"/paper/blindly-assess-quality-of-in-the-wild-videos","paper_url":"https://arxiv.org/abs/2108.08505v2","paper_title":"Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception","code":"https://github.com/zwx8981/tcsvt-2022-bvqa","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"LINEARITY","metrics":{"KLCC":"0.7589","PLCC":"0.9106","SRCC":"0.9104","Type":"NR"},"uses_additional_data":false,"paper_date":"2020-08-10","paper":"/paper/norm-in-norm-loss-with-faster-convergence-and","paper_url":"https://arxiv.org/abs/2008.03889v1","paper_title":"Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessment","code":"https://github.com/lidq92/LinearityIQA","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":6,"model":"VSFA","metrics":{"KLCC":"0.7483","PLCC":"0.9180","SRCC":"0.9049","Type":"NR"},"uses_additional_data":false,"paper_date":"2019-08-01","paper":"/paper/quality-assessment-of-in-the-wild-videos","paper_url":"https://arxiv.org/abs/1908.00375v3","paper_title":"Quality Assessment of In-the-Wild Videos","code":"https://github.com/lidq92/VSFA","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"MUSIQ","metrics":{"KLCC":"0.7433","PLCC":"0.9068","SRCC":"0.9004","Type":"NR"},"uses_additional_data":false,"paper_date":"2021-08-12","paper":"/paper/musiq-multi-scale-image-quality-transformer","paper_url":"https://arxiv.org/abs/2108.05997v1","paper_title":"MUSIQ: Multi-scale Image Quality Transformer","code":"https://github.com/google-research/google-research/tree/master/musiq","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":8,"model":"DOVER","metrics":{"KLCC":"0.7216","PLCC":"0.9099","SRCC":"0.8871","Type":"NR"},"uses_additional_data":false,"paper_date":"2022-11-09","paper":"/paper/disentangling-aesthetic-and-technical-effects","paper_url":"https://arxiv.org/abs/2211.04894v3","paper_title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","code":"https://github.com/vqassessment/dover","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":9,"model":"SPAQ MT-S","metrics":{"KLCC":"0.7186","PLCC":"0.8814","SRCC":"0.8822","Type":"NR"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/perceptual-quality-assessment-of-smartphone","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Fang_Perceptual_Quality_Assessment_of_Smartphone_Photography_CVPR_2020_paper.html","paper_title":"Perceptual Quality Assessment of Smartphone Photography","code":"https://github.com/h4nwei/SPAQ","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"SPAQ BL","metrics":{"KLCC":"0.7106","PLCC":"0.8855","SRCC":"0.8799","Type":"NR"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/perceptual-quality-assessment-of-smartphone","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Fang_Perceptual_Quality_Assessment_of_Smartphone_Photography_CVPR_2020_paper.html","paper_title":"Perceptual Quality Assessment of Smartphone Photography","code":"https://github.com/h4nwei/SPAQ","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"SPAQ MT-A","metrics":{"KLCC":"0.7148","PLCC":"0.8824","SRCC":"0.8794","Type":"NR"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/perceptual-quality-assessment-of-smartphone","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Fang_Perceptual_Quality_Assessment_of_Smartphone_Photography_CVPR_2020_paper.html","paper_title":"Perceptual Quality Assessment of Smartphone Photography","code":"https://github.com/h4nwei/SPAQ","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"GVSP-UGCVQA-NR (single_scale)","metrics":{"KLCC":"0.7037","PLCC":"0.8933","SRCC":"0.8742","Type":"NR"},"uses_additional_data":false,"paper_date":"2021-06-02","paper":"/paper/deep-learning-based-full-reference-and-no","paper_url":"https://arxiv.org/abs/2106.01111v1","paper_title":"Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos","code":"https://github.com/sunwei925/CompressedVQA","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"PaQ-2-PiQ","metrics":{"KLCC":"0.7079","PLCC":"0.8549","SRCC":"0.8705","Type":"NR"},"uses_additional_data":false,"paper_date":"2019-12-20","paper":"/paper/from-patches-to-pictures-paq-2-piq-mapping","paper_url":"https://arxiv.org/abs/1912.10088v1","paper_title":"From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality","code":"https://github.com/baidut/PaQ-2-PiQ","n_code_links":2,"syntology":null},{"rank_in_archive_order":14,"model":"GVSP-UGCVQA-NR (multi_scale)","metrics":{"KLCC":"0.6942","PLCC":"0.8851","SRCC":"0.8673","Type":"NR"},"uses_additional_data":false,"paper_date":"2021-06-02","paper":"/paper/deep-learning-based-full-reference-and-no","paper_url":"https://arxiv.org/abs/2106.01111v1","paper_title":"Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos","code":"https://github.com/sunwei925/CompressedVQA","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"NIMA","metrics":{"KLCC":"0.6745","PLCC":"0.8784","SRCC":"0.8494","Type":"NR"},"uses_additional_data":false,"paper_date":"2017-09-15","paper":"/paper/nima-neural-image-assessment","paper_url":"http://arxiv.org/abs/1709.05424v2","paper_title":"NIMA: Neural Image Assessment","code":"https://github.com/idealo/image-quality-assessment","n_code_links":12,"syntology":null},{"rank_in_archive_order":16,"model":"KonCept512","metrics":{"KLCC":"0.6608","PLCC":"0.8464","SRCC":"0.8360","Type":"NR"},"uses_additional_data":false,"paper_date":"2019-10-14","paper":"/paper/koniq-10k-an-ecologically-valid-database-for","paper_url":"https://arxiv.org/abs/1910.06180v2","paper_title":"KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment","code":"https://github.com/subpic/koniq","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"FAST-VQA","metrics":{"KLCC":"0.6498","PLCC":"0.8613","SRCC":"0.8308","Type":"NR"},"uses_additional_data":false,"paper_date":"2022-07-06","paper":"/paper/fast-vqa-efficient-end-to-end-video-quality","paper_url":"https://arxiv.org/abs/2207.02595v1","paper_title":"FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling","code":"https://github.com/VQAssessment/FAST-VQA-and-FasterVQA","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":18,"model":"FASTER-VQA","metrics":{"KLCC":"0.5645","PLCC":"0.8087","SRCC":"0.7508","Type":"NR"},"uses_additional_data":false,"paper_date":"2022-07-06","paper":"/paper/fast-vqa-efficient-end-to-end-video-quality","paper_url":"https://arxiv.org/abs/2207.02595v1","paper_title":"FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling","code":"https://github.com/VQAssessment/FAST-VQA-and-FasterVQA","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":19,"model":"VIDEVAL","metrics":{"KLCC":"0.5414","PLCC":"0.7717","SRCC":"0.7286","Type":"NR"},"uses_additional_data":false,"paper_date":"2020-05-29","paper":"/paper/ugc-vqa-benchmarking-blind-video-quality","paper_url":"https://arxiv.org/abs/2005.14354v2","paper_title":"UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content","code":"https://github.com/tu184044109/VIDEVAL_release","n_code_links":5,"syntology":null},{"rank_in_archive_order":20,"model":"Y-NIQE","metrics":{"KLCC":"0.4215","PLCC":"0.6713","SRCC":"0.5985","Type":"NR"},"uses_additional_data":false,"paper_date":"2019-07-08","paper":"/paper/barriers-towards-no-reference-metrics","paper_url":"https://arxiv.org/abs/1907.03842v2","paper_title":"Barriers towards no-reference metrics application to compressed video quality analysis: on the example of no-reference metric NIQE","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"MEON","metrics":{"KLCC":"0.3775","PLCC":"0.2898","SRCC":"0.5066","Type":"NR"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null}],"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":8,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":7,"samples_over_distinct_papers":{"n_ran":21,"n_unverified":11,"n_samples":32,"n_pointer_only_licence":17,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":23,"n_unverified":14,"n_samples":37,"n_pointer_only_licence":22,"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"}}}