{"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":"/task/self-supervised-action-recognition","name":"Self-Supervised Action Recognition","slug":"self-supervised-action-recognition","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":51,"papers_with_code":35,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101","slug":"self-supervised-action-recognition-on-ucf101","dataset":"UCF101","dataset_url":"/dataset/ucf101","rows_in_archive":53,"metrics":["3-fold Accuracy","Pre-Training Dataset","Frozen","split-1  Top-1 Accuracy"],"first_row_in_archive_order":{"model":"VideoMAE V2-g","paper_title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","paper_url":"/paper/videomae-v2-scaling-video-masked-autoencoders","paper_date":"2023-03-29","arxiv_id":"2303.16727","code_links":[{"title":"OpenGVLab/VideoMAEv2","url":"https://github.com/OpenGVLab/VideoMAEv2"}],"syntology":{"n":6,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/videomae-v2-scaling-video-masked-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2303.16727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16727"}},"official":{"repos":["OpenGVLab/VideoMAEv2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51","slug":"self-supervised-action-recognition-on-hmdb51","dataset":"HMDB51","dataset_url":"/dataset/hmdb51","rows_in_archive":48,"metrics":["Top-1 Accuracy","Pre-Training Dataset","Frozen"],"first_row_in_archive_order":{"model":"MVD (ViT-B)","paper_title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","paper_url":"/paper/masked-video-distillation-rethinking-masked","paper_date":"2022-12-08","arxiv_id":"2212.04500","code_links":[{"title":"ruiwang2021/mvd","url":"https://github.com/ruiwang2021/mvd"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/MVD"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/MVD"},{"title":"Mind23-2/MindCode-101","url":"https://github.com/Mind23-2/MindCode-101/tree/main/MVD"}],"syntology":null}},{"leaderboard":"/sota/self-supervised-action-recognition-on-hmdb51-1","slug":"self-supervised-action-recognition-on-hmdb51-1","dataset":"HMDB51 (finetuned)","dataset_url":"/dataset/hmdb51","rows_in_archive":14,"metrics":["Top-1 Accuracy","Pretraining Dataset"],"first_row_in_archive_order":{"model":"BraVe:V-FA (TSM-50x2)","paper_title":"Broaden Your Views for Self-Supervised Video Learning","paper_url":"/paper/broaden-your-views-for-self-supervised-video","paper_date":"2021-03-30","arxiv_id":"2103.16559","code_links":[{"title":"deepmind/brave","url":"https://github.com/deepmind/brave"}],"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/broaden-your-views-for-self-supervised-video#ran","syntology_url":"https://syntology.ai/paper/2103.16559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16559"}},"official":{"repos":["deepmind/brave"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/self-supervised-action-recognition-on-ucf101-1","slug":"self-supervised-action-recognition-on-ucf101-1","dataset":"UCF101 (finetuned)","dataset_url":"/dataset/ucf101","rows_in_archive":14,"metrics":["3-fold Accuracy","Pretrain"],"first_row_in_archive_order":{"model":"BraVe:V-FA (TSM-50x2)","paper_title":"Broaden Your Views for Self-Supervised Video Learning","paper_url":"/paper/broaden-your-views-for-self-supervised-video","paper_date":"2021-03-30","arxiv_id":"2103.16559","code_links":[{"title":"deepmind/brave","url":"https://github.com/deepmind/brave"}],"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/broaden-your-views-for-self-supervised-video#ran","syntology_url":"https://syntology.ai/paper/2103.16559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16559"}},"official":{"repos":["deepmind/brave"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/self-supervised-action-recognition-on","slug":"self-supervised-action-recognition-on","dataset":"Kinetics-600","dataset_url":"/dataset/kinetics-600","rows_in_archive":5,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"CVRL (R3D-152 2x)","paper_title":"Spatiotemporal Contrastive Video Representation Learning","paper_url":"/paper/spatiotemporal-contrastive-video","paper_date":"2020-08-09","arxiv_id":"2008.03800","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/projects/video_ssl"},{"title":"ed-fish/spatio-temporal-contrastive-film","url":"https://github.com/ed-fish/spatio-temporal-contrastive-film"},{"title":"ed-fish/spatio-temporal-contrastive-video","url":"https://github.com/ed-fish/spatio-temporal-contrastive-video"},{"title":"applecrumble123/CVLR_pytorch","url":"https://github.com/applecrumble123/CVLR_pytorch"}],"syntology":null}},{"leaderboard":"/sota/self-supervised-action-recognition-on-1","slug":"self-supervised-action-recognition-on-1","dataset":"Kinetics-400","dataset_url":"/dataset/kinetics","rows_in_archive":4,"metrics":["Top-1 accuracy %","Top-5 Accuracy %"],"first_row_in_archive_order":{"model":"XKD (ViT-B/112/16)","paper_title":"XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning","paper_url":"/paper/xkd-cross-modal-knowledge-distillation-with","paper_date":"2022-11-25","arxiv_id":"2211.13929","code_links":[{"title":"pritamqu/XKD","url":"https://github.com/pritamqu/XKD"}],"syntology":null}}],"datasets":[{"url":"/dataset/ucf101","name":"UCF101","full_name":"UCF101 Human Actions dataset","num_papers_in_archive":1863},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/hmdb51","name":"HMDB51","full_name":"","num_papers_in_archive":839},{"url":"/dataset/kinetics-400-1","name":"Kinetics 400","full_name":"","num_papers_in_archive":712},{"url":"/dataset/kinetics-600","name":"Kinetics-600","full_name":"","num_papers_in_archive":148}],"subtasks":[],"parent_tasks":[{"url":"/task/action-recognition-in-videos","name":"Action Recognition"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":51,"of":51,"of_with_code":35,"tagged_in_all":51,"counts":{"archive_papers_tagged":51,"with_a_code_link":35,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":51,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":9,"listed_every_run_a_failure_of_syntologys_instrument":3,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/videomae-masked-autoencoders-are-data-1","slug":"videomae-masked-autoencoders-are-data-1","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","date":"2022-03-23","arxiv_id":"2203.12602","repositories_listed":9,"syntology":{"n":13,"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}},"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/contrastive-multiview-coding","slug":"contrastive-multiview-coding","title":"Contrastive Multiview Coding","date":"2019-06-13","arxiv_id":"1906.05849","repositories_listed":8,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contrastive-multiview-coding#ran","syntology_url":"https://syntology.ai/paper/1906.05849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05849"}},"official":{"repos":["HobbitLong/CMC"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/masked-video-distillation-rethinking-masked","slug":"masked-video-distillation-rethinking-masked","title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","date":"2022-12-08","arxiv_id":"2212.04500","repositories_listed":4,"syntology":null},{"url":"/paper/spatiotemporal-contrastive-video","slug":"spatiotemporal-contrastive-video","title":"Spatiotemporal Contrastive Video Representation Learning","date":"2020-08-09","arxiv_id":"2008.03800","repositories_listed":4,"syntology":null},{"url":"/paper/joint-adversarial-and-collaborative-learning","slug":"joint-adversarial-and-collaborative-learning","title":"Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition","date":"2023-07-15","arxiv_id":"2307.07791","repositories_listed":2,"syntology":null},{"url":"/paper/similarity-contrastive-estimation-for-image","slug":"similarity-contrastive-estimation-for-image","title":"Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning","date":"2022-12-21","arxiv_id":"2212.11187","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-video-representation-learning-via","slug":"efficient-video-representation-learning-via","title":"EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens","date":"2022-11-19","arxiv_id":"2211.10636","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/efficient-video-representation-learning-via#ran","syntology_url":"https://syntology.ai/paper/2211.10636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10636"}},"official":{"repos":["sunilhoho/everest","sunilhoho/VideoMS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/m-3-video-masked-motion-modeling-for-self","slug":"m-3-video-masked-motion-modeling-for-self","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","date":"2022-10-12","arxiv_id":"2210.06096","repositories_listed":2,"syntology":null},{"url":"/paper/a-large-scale-study-on-unsupervised","slug":"a-large-scale-study-on-unsupervised","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","date":"2021-04-29","arxiv_id":"2104.14558","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-3","slug":"self-supervised-video-representation-learning-3","title":"Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework","date":"2020-08-06","arxiv_id":"2008.02531","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-video-representation-learning-3#ran","syntology_url":"https://syntology.ai/paper/2008.02531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02531"}},"official":{"repos":["BestJuly/Inter-intra-video-contrastive-learning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/part-aware-contrastive-learning-for-self","slug":"part-aware-contrastive-learning-for-self","title":"Part Aware Contrastive Learning for Self-Supervised Action Recognition","date":"2023-05-01","arxiv_id":"2305.00666","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/part-aware-contrastive-learning-for-self#ran","syntology_url":"https://syntology.ai/paper/2305.00666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00666"}},"official":{"repos":["githubofhyl97/skeattnclr"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/videomae-v2-scaling-video-masked-autoencoders","slug":"videomae-v2-scaling-video-masked-autoencoders","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","date":"2023-03-29","arxiv_id":"2303.16727","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/videomae-v2-scaling-video-masked-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2303.16727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16727"}},"official":{"repos":["OpenGVLab/VideoMAEv2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-action-representation","slug":"self-supervised-action-representation","title":"Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences","date":"2023-02-17","arxiv_id":"2302.09018","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-action-representation#ran","syntology_url":"https://syntology.ai/paper/2302.09018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.09018"}},"official":{"repos":["yujieouo/pstl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/xkd-cross-modal-knowledge-distillation-with","slug":"xkd-cross-modal-knowledge-distillation-with","title":"XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning","date":"2022-11-25","arxiv_id":"2211.13929","repositories_listed":1,"syntology":null},{"url":"/paper/slic-self-supervised-learning-with-iterative-1","slug":"slic-self-supervised-learning-with-iterative-1","title":"SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos","date":"2022-06-25","arxiv_id":"2206.12534","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-from-extremely-augmented","slug":"contrastive-learning-from-extremely-augmented","title":"Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition","date":"2021-12-07","arxiv_id":"2112.03590","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-audio-visual-representation","slug":"self-supervised-audio-visual-representation","title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","date":"2021-11-09","arxiv_id":"2111.05329","repositories_listed":1,"syntology":null},{"url":"/paper/learning-the-predictability-of-the-future","slug":"learning-the-predictability-of-the-future","title":"Learning the Predictability of the Future","date":"2021-06-19","arxiv_id":"2101.01600","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/learning-the-predictability-of-the-future#ran","syntology_url":"https://syntology.ai/paper/2101.01600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.01600"}},"official":{"repos":["cvlab-columbia/hyperfuture"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/self-supervised-video-representation-learning-7","slug":"self-supervised-video-representation-learning-7","title":"Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting","date":"2021-06-18","arxiv_id":"2106.10137","repositories_listed":1,"syntology":null},{"url":"/paper/broaden-your-views-for-self-supervised-video","slug":"broaden-your-views-for-self-supervised-video","title":"Broaden Your Views for Self-Supervised Video Learning","date":"2021-03-30","arxiv_id":"2103.16559","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/broaden-your-views-for-self-supervised-video#ran","syntology_url":"https://syntology.ai/paper/2103.16559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16559"}},"official":{"repos":["deepmind/brave"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tclr-temporal-contrastive-learning-for-video","slug":"tclr-temporal-contrastive-learning-for-video","title":"TCLR: Temporal Contrastive Learning for Video Representation","date":"2021-01-20","arxiv_id":"2101.07974","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/tclr-temporal-contrastive-learning-for-video#ran","syntology_url":"https://syntology.ai/paper/2101.07974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.07974"}},"official":{"repos":["DAVEISHAN/TCLR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/self-supervised-video-representation-using","slug":"self-supervised-video-representation-using","title":"Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning","date":"2020-10-29","arxiv_id":"2010.15464","repositories_listed":1,"syntology":null},{"url":"/paper/rspnet-relative-speed-perception-for","slug":"rspnet-relative-speed-perception-for","title":"RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning","date":"2020-10-27","arxiv_id":"2011.07949","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-co-training-for-video","slug":"self-supervised-co-training-for-video","title":"Self-supervised Co-training for Video Representation Learning","date":"2020-10-19","arxiv_id":"2010.09709","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-co-training-for-video#ran","syntology_url":"https://syntology.ai/paper/2010.09709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09709"}},"official":{"repos":["TengdaHan/CoCLR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-multimodal-versatile-networks","slug":"self-supervised-multimodal-versatile-networks","title":"Self-Supervised MultiModal Versatile Networks","date":"2020-06-29","arxiv_id":"2006.16228","repositories_listed":1,"syntology":null},{"url":"/paper/video-playback-rate-perception-for-self","slug":"video-playback-rate-perception-for-self","title":"Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation Learning","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-instance-discrimination-with","slug":"audio-visual-instance-discrimination-with","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","date":"2020-04-27","arxiv_id":"2004.12943","repositories_listed":1,"syntology":null},{"url":"/paper/speednet-learning-the-speediness-in-videos","slug":"speednet-learning-the-speediness-in-videos","title":"SpeedNet: Learning the Speediness in Videos","date":"2020-04-13","arxiv_id":"2004.06130","repositories_listed":1,"syntology":null},{"url":"/paper/temporally-coherent-embeddings-for-self","slug":"temporally-coherent-embeddings-for-self","title":"Temporally Coherent Embeddings for Self-Supervised Video Representation Learning","date":"2020-03-21","arxiv_id":"2004.02753","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/temporally-coherent-embeddings-for-self#ran","syntology_url":"https://syntology.ai/paper/2004.02753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.02753"}},"official":{"repos":["csiro-robotics/TCE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/self-supervised-spatio-temporal-2","slug":"self-supervised-spatio-temporal-2","title":"Self-Supervised Visual Learning by Variable Playback Speeds Prediction of a Video","date":"2020-03-05","arxiv_id":"2003.02692","repositories_listed":1,"syntology":null},{"url":"/paper/video-cloze-procedure-for-self-supervised","slug":"video-cloze-procedure-for-self-supervised","title":"Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning","date":"2020-01-02","arxiv_id":"2001.00294","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-cloze-procedure-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2001.00294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00294"}},"official":null}},{"url":"/paper/self-supervised-learning-by-cross-modal-audio","slug":"self-supervised-learning-by-cross-modal-audio","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","date":"2019-11-28","arxiv_id":"1911.12667","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/self-supervised-learning-by-cross-modal-audio#ran","syntology_url":"https://syntology.ai/paper/1911.12667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12667"}},"official":{"repos":["HumamAlwassel/XDC"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/video-representation-learning-by-dense","slug":"video-representation-learning-by-dense","title":"Video Representation Learning by Dense Predictive Coding","date":"2019-09-10","arxiv_id":"1909.04656","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-representation-learning-by-dense#ran","syntology_url":"https://syntology.ai/paper/1909.04656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04656"}},"official":{"repos":["TengdaHan/DPC"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-spatio-temporal","slug":"self-supervised-spatio-temporal","title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","date":"2019-04-07","arxiv_id":"1904.03597","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-representation-learning-by","slug":"unsupervised-representation-learning-by","title":"Unsupervised Representation Learning by Sorting Sequences","date":"2017-08-03","arxiv_id":"1708.01246","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-representation-learning-by#ran","syntology_url":"https://syntology.ai/paper/1708.01246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.01246"}},"official":{"repos":["HsinYingLee/OPN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":null,"slug":"feature-hallucination-for-self-supervised","title":"Feature Hallucination for Self-supervised Action Recognition","date":"2025-06-25","arxiv_id":"2506.20342","repositories_listed":0,"syntology":null},{"url":"/paper/benchmarking-self-supervised-video","slug":"benchmarking-self-supervised-video","title":"A Large-Scale Analysis on Self-Supervised Video Representation Learning","date":"2023-06-09","arxiv_id":"2306.06010","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-contrastive-learning-for-self","title":"Self-supervised Contrastive Learning for Audio-Visual Action Recognition","date":"2022-04-28","arxiv_id":"2204.13386","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-centered-prior-guided-and-task","title":"Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training","date":"2022-04-27","arxiv_id":"2204.12729","repositories_listed":0,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-8","slug":"self-supervised-video-representation-learning-8","title":"Self-Supervised Video Representation Learning with Meta-Contrastive Network","date":"2021-08-19","arxiv_id":"2108.08426","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-via-multi","title":"Self-Supervised Learning via multi-Transformation Classification for Action Recognition","date":"2021-02-20","arxiv_id":"2102.10378","repositories_listed":0,"syntology":null},{"url":"/paper/evolving-losses-for-unsupervised-video","slug":"evolving-losses-for-unsupervised-video","title":"Evolving Losses for Unsupervised Video Representation Learning","date":"2020-02-26","arxiv_id":"2002.12177","repositories_listed":0,"syntology":null},{"url":"/paper/skip-clip-self-supervised-spatiotemporal","slug":"skip-clip-self-supervised-spatiotemporal","title":"Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking","date":"2019-10-28","arxiv_id":"1910.12770","repositories_listed":0,"syntology":null},{"url":"/paper/self-supervised-spatiotemporal-learning-via","slug":"self-supervised-spatiotemporal-learning-via","title":"Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/self-supervised-spatiotemporal-feature","slug":"self-supervised-spatiotemporal-feature","title":"Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction","date":"2018-11-28","arxiv_id":"1811.11387","repositories_listed":0,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning","slug":"self-supervised-video-representation-learning","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","date":"2018-11-24","arxiv_id":"1811.09795","repositories_listed":0,"syntology":null},{"url":"/paper/cooperative-learning-of-audio-and-video","slug":"cooperative-learning-of-audio-and-video","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","date":"2018-06-30","arxiv_id":"1807.00230","repositories_listed":0,"syntology":null},{"url":"/paper/learning-and-using-the-arrow-of-time","slug":"learning-and-using-the-arrow-of-time","title":"Learning and Using the Arrow of Time","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-1","slug":"self-supervised-video-representation-learning-1","title":"Self-Supervised Video Representation Learning With Odd-One-Out Networks","date":"2016-11-21","arxiv_id":"1611.06646","repositories_listed":0,"syntology":null},{"url":"/paper/generating-videos-with-scene-dynamics","slug":"generating-videos-with-scene-dynamics","title":"Generating Videos with Scene Dynamics","date":"2016-09-08","arxiv_id":"1609.02612","repositories_listed":0,"syntology":null},{"url":"/paper/shuffle-and-learn-unsupervised-learning-using","slug":"shuffle-and-learn-unsupervised-learning-using","title":"Shuffle and Learn: Unsupervised Learning using Temporal Order Verification","date":"2016-03-28","arxiv_id":"1603.08561","repositories_listed":0,"syntology":null}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_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_where_code_ran":12,"papers_where_code_ran_first_page":"/task/self-supervised-action-recognition/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/self-supervised-action-recognition/papers/ran/1","json":"/task/self-supervised-action-recognition/papers/ran/1.json","rows":12}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"ab4908e5826e9718385f09e166c6caa1b3b1002b3ae38d5881ad55e1e41b63ab","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}