{"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/posetrack","name":"PoseTrack","full_name":null,"description_markdown":"The **PoseTrack** dataset is a large-scale benchmark for multi-person pose estimation and tracking in videos. It requires not only pose estimation in single frames, but also temporal tracking across frames. It contains 514 videos including 66,374 frames in total, split into 300, 50 and 208 videos for training, validation and test set respectively. For training videos, 30 frames from the center are annotated. For validation and test videos, besides 30 frames from the center, every fourth frame is also annotated for evaluating long range articulated tracking. The annotations include 15 body keypoints location, a unique person id and a head bounding box for each person instance.\r\n\r\nSource: [Simple Baselines for Human Pose Estimation and Tracking](https://arxiv.org/abs/1804.06208)\r\nImage Source: [https://posetrack.net/](https://posetrack.net/)","description_withheld":null,"homepage":"https://posetrack.net/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/posetrack-a-benchmark-for-human-pose","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","first_author":"Mykhaylo Andriluka","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Tracking","url":"/datasets/modality/tracking"}],"tasks":[{"name":"Pose Tracking","url":"/task/pose-tracking","datasets_with_task":"/datasets/task/pose-tracking"},{"name":"Multi-Person Pose Estimation","url":"/task/multi-person-pose-estimation","datasets_with_task":"/datasets/task/multi-person-pose-estimation"},{"name":"Multi-Person Pose Estimation and Tracking","url":"/task/multi-person-pose-estimation-and-tracking","datasets_with_task":"/datasets/task/multi-person-pose-estimation-and-tracking"}],"languages":[],"variants":["PoseTrack2017","PoseTrack2018","PoseTrack"],"data_loaders":[{"repo":"https://github.com/open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose/blob/master/docs/tasks/2d_body_keypoint.md#posetrack18","frameworks":["pytorch"]}],"num_papers_in_archive":103,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/pose-tracking-on-posetrack2017","task":"Pose Tracking","dataset_variant":"PoseTrack2017","rows":10,"metrics":["MOTA","mAP"],"first_row_in_archive_order":{"model":"DetTrack","paper":"/paper/combining-detection-and-tracking-for-human","metrics":{"MOTA":"64.09","mAP":"74.14"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/pose-tracking-on-posetrack2018","task":"Pose Tracking","dataset_variant":"PoseTrack2018","rows":5,"metrics":["MOTA","mAP","IDF1","IDs"],"first_row_in_archive_order":{"model":"DetTrack","paper":"/paper/combining-detection-and-tracking-for-human","metrics":{"MOTA":"64.3","mAP":"73.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-person-pose-estimation-on-posetrack2018","task":"Multi-Person Pose Estimation","dataset_variant":"PoseTrack2018","rows":4,"metrics":["Mean mAP"],"first_row_in_archive_order":{"model":"Poseidon","paper":"/paper/poseidon-a-vit-based-architecture-for-multi","metrics":{"Mean mAP":"87.8"},"code_links":[{"title":"CesareDavidePace/poseidon","url":"https://github.com/CesareDavidePace/poseidon"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-person-pose-estimation-on-posetrack2017","task":"Multi-Person Pose Estimation","dataset_variant":"PoseTrack2017","rows":3,"metrics":["Mean mAP"],"first_row_in_archive_order":{"model":"DCPose","paper":"/paper/deep-dual-consecutive-network-for-human-pose","metrics":{"Mean mAP":"79.2"},"code_links":[{"title":"Pose-Group/DCPose","url":"https://github.com/Pose-Group/DCPose"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-person-pose-estimation-and-tracking-on-1","task":"Multi-Person Pose Estimation and Tracking","dataset_variant":"PoseTrack2018","rows":1,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"Refine","paper":"/paper/learning-to-refine-human-pose-estimation","metrics":{"MOTA":"58.4"},"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":16,"of":16,"counts":{"papers_with_a_benchmark_row":16,"with_a_code_link":11,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":16,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/poseidon-a-vit-based-architecture-for-multi","slug":"poseidon-a-vit-based-architecture-for-multi","title":"Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion","date":"2025-01-14","arxiv_id":"2501.08446","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/humans-in-4d-reconstructing-and-tracking","slug":"humans-in-4d-reconstructing-and-tracking","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","date":"2023-05-31","arxiv_id":"2305.20091","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":1,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["shubham-goel/4D-Humans"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"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/humans-in-4d-reconstructing-and-tracking#ran","syntology_url":"https://syntology.ai/paper/2305.20091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.20091"}}}},{"paper":"/paper/do-different-tracking-tasks-require-different","slug":"do-different-tracking-tasks-require-different","title":"Do Different Tracking Tasks Require Different Appearance Models?","date":"2021-07-05","arxiv_id":"2107.02156","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":6,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["Zhongdao/UniTrack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":11,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/do-different-tracking-tasks-require-different#ran","syntology_url":"https://syntology.ai/paper/2107.02156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02156"}}}},{"paper":"/paper/deep-dual-consecutive-network-for-human-pose","slug":"deep-dual-consecutive-network-for-human-pose","title":"Deep Dual Consecutive Network for Human Pose Estimation","date":"2021-03-12","arxiv_id":"2103.07254","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":9,"samples_ran_checked":9,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":13,"official":{"repos":["Pose-Group/DCPose"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":9,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-dual-consecutive-network-for-human-pose#ran","syntology_url":"https://syntology.ai/paper/2103.07254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07254"}}}},{"paper":"/paper/combining-detection-and-tracking-for-human","slug":"combining-detection-and-tracking-for-human","title":"Combining detection and tracking for human pose estimation in videos","date":"2020-03-30","arxiv_id":"2003.13743","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/15-keypoints-is-all-you-need","slug":"15-keypoints-is-all-you-need","title":"15 Keypoints Is All You Need","date":"2019-12-05","arxiv_id":"1912.02323","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-temporal-pose-estimation-from","slug":"learning-temporal-pose-estimation-from","title":"Learning Temporal Pose Estimation from Sparsely-Labeled Videos","date":"2019-06-06","arxiv_id":"1906.04016","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/pose-estimator-and-tracker-using-temporal","slug":"pose-estimator-and-tracker-using-temporal","title":"Pose estimator and tracker using temporal flow maps for limbs","date":"2019-05-23","arxiv_id":"1905.09500","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/lighttrack-a-generic-framework-for-online-top","slug":"lighttrack-a-generic-framework-for-online-top","title":"LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking","date":"2019-05-07","arxiv_id":"1905.02822","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":1,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["Guanghan/lighttrack"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lighttrack-a-generic-framework-for-online-top#ran","syntology_url":"https://syntology.ai/paper/1905.02822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.02822"}}}},{"paper":"/paper/deep-high-resolution-representation-learning","slug":"deep-high-resolution-representation-learning","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","date":"2019-02-25","arxiv_id":"1902.09212","rows_on_this_dataset":1,"code_links":39,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":8,"samples_unverified":9,"pointer_only_for_licence":2,"official":{"repos":["leoxiaobin/deep-high-resolution-net.pytorch","Microsoft/human-pose-estimation.pytorch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-high-resolution-representation-learning#ran","syntology_url":"https://syntology.ai/paper/1902.09212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09212"}}}},{"paper":"/paper/efficient-online-multi-person-2d-pose","slug":"efficient-online-multi-person-2d-pose","title":"Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields","date":"2018-11-29","arxiv_id":"1811.11975","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-to-refine-human-pose-estimation","slug":"learning-to-refine-human-pose-estimation","title":"Learning to Refine Human Pose Estimation","date":"2018-04-21","arxiv_id":"1804.07909","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/simple-baselines-for-human-pose-estimation","slug":"simple-baselines-for-human-pose-estimation","title":"Simple Baselines for Human Pose Estimation and Tracking","date":"2018-04-17","arxiv_id":"1804.06208","rows_on_this_dataset":2,"code_links":27,"syntology":null},{"paper":"/paper/pose-flow-efficient-online-pose-tracking","slug":"pose-flow-efficient-online-pose-tracking","title":"Pose Flow: Efficient Online Pose Tracking","date":"2018-02-03","arxiv_id":"1802.00977","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/detect-and-track-efficient-pose-estimation-in","slug":"detect-and-track-efficient-pose-estimation-in","title":"Detect-and-Track: Efficient Pose Estimation in Videos","date":"2017-12-26","arxiv_id":"1712.09184","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/posetrack-a-benchmark-for-human-pose","slug":"posetrack-a-benchmark-for-human-pose","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","date":"2017-10-27","arxiv_id":"1710.10000","rows_on_this_dataset":2,"code_links":2,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/poseidon-a-vit-based-architecture-for-multi","slug":"poseidon-a-vit-based-architecture-for-multi","title":"Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion","date":"2025-01-14","arxiv_id":"2501.08446","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/humans-in-4d-reconstructing-and-tracking","slug":"humans-in-4d-reconstructing-and-tracking","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","date":"2023-05-31","arxiv_id":"2305.20091","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":1,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["shubham-goel/4D-Humans"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"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/humans-in-4d-reconstructing-and-tracking#ran","syntology_url":"https://syntology.ai/paper/2305.20091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.20091"}}}},{"paper":"/paper/do-different-tracking-tasks-require-different","slug":"do-different-tracking-tasks-require-different","title":"Do Different Tracking Tasks Require Different Appearance Models?","date":"2021-07-05","arxiv_id":"2107.02156","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":6,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["Zhongdao/UniTrack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":11,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/do-different-tracking-tasks-require-different#ran","syntology_url":"https://syntology.ai/paper/2107.02156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02156"}}}},{"paper":"/paper/deep-dual-consecutive-network-for-human-pose","slug":"deep-dual-consecutive-network-for-human-pose","title":"Deep Dual Consecutive Network for Human Pose Estimation","date":"2021-03-12","arxiv_id":"2103.07254","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":9,"samples_ran_checked":9,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":13,"official":{"repos":["Pose-Group/DCPose"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":9,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-dual-consecutive-network-for-human-pose#ran","syntology_url":"https://syntology.ai/paper/2103.07254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07254"}}}},{"paper":"/paper/combining-detection-and-tracking-for-human","slug":"combining-detection-and-tracking-for-human","title":"Combining detection and tracking for human pose estimation in videos","date":"2020-03-30","arxiv_id":"2003.13743","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/15-keypoints-is-all-you-need","slug":"15-keypoints-is-all-you-need","title":"15 Keypoints Is All You Need","date":"2019-12-05","arxiv_id":"1912.02323","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-temporal-pose-estimation-from","slug":"learning-temporal-pose-estimation-from","title":"Learning Temporal Pose Estimation from Sparsely-Labeled Videos","date":"2019-06-06","arxiv_id":"1906.04016","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/pose-estimator-and-tracker-using-temporal","slug":"pose-estimator-and-tracker-using-temporal","title":"Pose estimator and tracker using temporal flow maps for limbs","date":"2019-05-23","arxiv_id":"1905.09500","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/lighttrack-a-generic-framework-for-online-top","slug":"lighttrack-a-generic-framework-for-online-top","title":"LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking","date":"2019-05-07","arxiv_id":"1905.02822","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":1,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["Guanghan/lighttrack"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lighttrack-a-generic-framework-for-online-top#ran","syntology_url":"https://syntology.ai/paper/1905.02822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.02822"}}}},{"paper":"/paper/deep-high-resolution-representation-learning","slug":"deep-high-resolution-representation-learning","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","date":"2019-02-25","arxiv_id":"1902.09212","rows_on_this_dataset":1,"code_links":39,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":8,"samples_unverified":9,"pointer_only_for_licence":2,"official":{"repos":["leoxiaobin/deep-high-resolution-net.pytorch","Microsoft/human-pose-estimation.pytorch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-high-resolution-representation-learning#ran","syntology_url":"https://syntology.ai/paper/1902.09212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09212"}}}},{"paper":"/paper/efficient-online-multi-person-2d-pose","slug":"efficient-online-multi-person-2d-pose","title":"Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields","date":"2018-11-29","arxiv_id":"1811.11975","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-to-refine-human-pose-estimation","slug":"learning-to-refine-human-pose-estimation","title":"Learning to Refine Human Pose Estimation","date":"2018-04-21","arxiv_id":"1804.07909","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/simple-baselines-for-human-pose-estimation","slug":"simple-baselines-for-human-pose-estimation","title":"Simple Baselines for Human Pose Estimation and Tracking","date":"2018-04-17","arxiv_id":"1804.06208","rows_on_this_dataset":2,"code_links":27,"syntology":null},{"paper":"/paper/pose-flow-efficient-online-pose-tracking","slug":"pose-flow-efficient-online-pose-tracking","title":"Pose Flow: Efficient Online Pose Tracking","date":"2018-02-03","arxiv_id":"1802.00977","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/detect-and-track-efficient-pose-estimation-in","slug":"detect-and-track-efficient-pose-estimation-in","title":"Detect-and-Track: Efficient Pose Estimation in Videos","date":"2017-12-26","arxiv_id":"1712.09184","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/posetrack-a-benchmark-for-human-pose","slug":"posetrack-a-benchmark-for-human-pose","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","date":"2017-10-27","arxiv_id":"1710.10000","rows_on_this_dataset":2,"code_links":2,"syntology":null}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/posetrack/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/posetrack/papers/ran/1","json":"/dataset/posetrack/papers/ran/1.json","rows":5}],"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":5,"samples_harvested":76,"samples_ran":48,"samples_constructed":14,"samples_ran_checked":35,"samples_ran_instrument_failed":13,"samples_unverified":28,"pointer_only_for_licence":15,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":5,"papers_where_every_run_was_an_instrument_failure":0,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"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":"20bb8581b4dd3566c6dbefb1d8cabfd97fd9a82288d431dad8ab114a4ea1f590","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}