{"id":"W4226042751","doi":"10.1609/aaai.v36i2.20047","title":"Self-Supervised Spatiotemporal Representation Learning by Exploiting Video Continuity","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Representation (politics); Feature learning; Context (archaeology); Artificial intelligence; Task (project management); Action (physics); Property (philosophy); Perception; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008834111,0.000611294,0.0006362979,0.000671728,0.000271718,0.0006856485,0.001414369,0.0008132069,0.00128868],"category_scores_gemma":[0.00338224,0.0004000285,0.0004939756,0.0006504485,0.0008726161,0.002210731,0.001287435,0.001355994,0.0003283907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000649875,"about_ca_system_score_gemma":0.0008130132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002815768,"about_ca_topic_score_gemma":0.003257076,"domain_scores_codex":[0.9995685,0.00009566424,0.00001847926,0.0001798051,0.00008590692,0.00005157569],"domain_scores_gemma":[0.9986468,0.0004889655,0.0002465562,0.0003075154,0.0002225013,0.00008768258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003970245,0.0002767908,0.004100052,0.0001350598,0.000109609,0.0001606911,0.000288725,0.516474,0.03104628,0.01644068,0.004853855,0.4257173],"study_design_scores_gemma":[0.000006235689,0.00003427795,0.0001837658,0.000002829822,0.000004146321,0.00001504399,0.00000816901,0.9944541,0.001890187,0.003186322,0.0002122793,0.000002606944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07525347,0.0001842356,0.9219969,0.0002053406,0.00002622603,0.00005198413,0.00009646459,0.0008899919,0.001295323],"genre_scores_gemma":[0.8636487,0.0001622776,0.1325428,0.0001697039,0.00007577793,0.00007546926,0.0006633421,0.0001367158,0.002525361],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002815768,"threshold_uncertainty_score":0.005598783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0675899898834621,"score_gpt":0.2891671634956185,"score_spread":0.2215771736121564,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}