{"id":"W4206004830","doi":"10.1109/tmm.2022.3141888","title":"Fast Human Pose Estimation in Compressed Videos","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","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); McMaster University","funders":"","keywords":"Computer science; Image warping; Artificial intelligence; Computer vision; Pose; Dynamic time warping; Frame (networking); Motion estimation; Inter frame; Discrete cosine transform; Motion (physics); Pattern recognition (psychology); Reference frame; Image (mathematics)","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":[0.000459925,0.001505779,0.000800516,0.001272393,0.0002759716,0.0005214024,0.0009408497,0.0006243899,0.003301098],"category_scores_gemma":[0.002690951,0.0004561009,0.0004184517,0.0007849016,0.0003753737,0.001082272,0.0008809473,0.0007635272,0.001205922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002956514,"about_ca_system_score_gemma":0.0004774914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007475177,"about_ca_topic_score_gemma":0.007079243,"domain_scores_codex":[0.9993587,0.00009515542,0.00001907651,0.0001517195,0.000307392,0.00006795893],"domain_scores_gemma":[0.9994709,0.000181635,0.00006324634,0.0000802295,0.0001758179,0.0000281384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004444344,0.00008513875,0.001151731,0.0002357725,0.00006603931,0.0003136303,0.0001388901,0.06549241,0.06892844,0.003840895,0.007749223,0.8515534],"study_design_scores_gemma":[0.0000317532,0.0001615948,0.00306869,0.00003813809,0.00003060428,0.0006683043,0.00008823926,0.9448114,0.03899627,0.006218607,0.005850926,0.00003551317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01438961,0.0007083265,0.981252,0.0001049062,0.000108614,0.00008665786,0.00026417,0.001810926,0.001274936],"genre_scores_gemma":[0.369461,0.002178967,0.6202713,0.0002933237,0.0003846291,0.0001830566,0.002280889,0.0002712056,0.004675721],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007475177,"threshold_uncertainty_score":0.01486331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02036827576848993,"score_gpt":0.2654056436825718,"score_spread":0.2450373679140819,"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."}}