{"url":"/sota/video-semantic-segmentation-on-camvid","task":{"name":"Video Semantic Segmentation","url":"/task/video-semantic-segmentation","note":null},"dataset":{"name":"CamVid","url":"/dataset/camvid"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"The goal of video semantic segmentation is to assign a predefined class to each pixel in all frames of a video. This requires the model not only to predict accurate segmentation masks but also to ensure that these masks remain temporally consistent across frames. This task has broad applications in areas such as autonomous driving, medical video analysis, and AR/VR.","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":["Mean IoU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Mean IoU":"higher"}},"counts":{"rows":6,"rows_with_code":5,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"TMANet-50","metrics":{"Mean IoU":"76.5"},"uses_additional_data":false,"paper_date":"2021-02-17","paper":"/paper/temporal-memory-attention-for-video-semantic","paper_url":"https://arxiv.org/abs/2102.08643v2","paper_title":"Temporal Memory Attention for Video Semantic Segmentation","code":"https://github.com/wanghao9610/TMANet","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"ETC-MobileNet","metrics":{"Mean IoU":"76.3"},"uses_additional_data":false,"paper_date":"2020-02-26","paper":"/paper/efficient-semantic-video-segmentation-with","paper_url":"https://arxiv.org/abs/2002.11433v2","paper_title":"Efficient Semantic Video Segmentation with Per-frame Inference","code":"https://github.com/irfanICMLL/ETC-Real-time-Per-frame-Semantic-video-segmentation","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":3,"model":"TDNet-50","metrics":{"Mean IoU":"76.2"},"uses_additional_data":false,"paper_date":"2020-04-03","paper":"/paper/temporally-distributed-networks-for-fast","paper_url":"https://arxiv.org/abs/2004.01800v2","paper_title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","code":"https://github.com/feinanshan/TDNet","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"PSPNet-50","metrics":{"Mean IoU":"76"},"uses_additional_data":false,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"syntology":{"n_ran":7,"n_unverified":22,"n_samples":29,"n_pointer_only_licence":5}},{"rank_in_archive_order":5,"model":"Netwarp","metrics":{"Mean IoU":"74.7"},"uses_additional_data":false,"paper_date":"2021-02-17","paper":"/paper/temporal-memory-attention-for-video-semantic","paper_url":"https://arxiv.org/abs/2102.08643v2","paper_title":"Temporal Memory Attention for Video Semantic Segmentation","code":"https://github.com/wanghao9610/TMANet","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"GRFP","metrics":{"Mean IoU":"67.1"},"uses_additional_data":false,"paper_date":"2016-12-28","paper":"/paper/semantic-video-segmentation-by-gated","paper_url":"http://arxiv.org/abs/1612.08871v2","paper_title":"Semantic Video Segmentation by Gated Recurrent Flow Propagation","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":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":12,"n_unverified":25,"n_samples":37,"n_pointer_only_licence":8,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":12,"n_unverified":25,"n_samples":37,"n_pointer_only_licence":8,"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"}}}