{"id":"W4292794024","doi":"10.1109/cvprw56347.2022.00055","title":"ActAR: Actor-Driven Pose Embeddings for Video Action Recognition","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Key (lock); Action (physics); Task (project management); Process (computing); Action recognition; Encoding (memory); Optical flow; Machine learning; Frame (networking); Pattern recognition (psychology); Human–computer interaction; Computer vision; 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":[0.00087241,0.002876917,0.001592659,0.001277926,0.0002895286,0.0007979479,0.002456149,0.001352182,0.005890052],"category_scores_gemma":[0.002456834,0.0006525454,0.001705878,0.001183976,0.0006688413,0.001939124,0.00161038,0.002312044,0.006488303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006626996,"about_ca_system_score_gemma":0.000750053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003741023,"about_ca_topic_score_gemma":0.00557281,"domain_scores_codex":[0.9989161,0.000224324,0.00004853192,0.0004955319,0.0002109679,0.0001044081],"domain_scores_gemma":[0.9993001,0.0001534858,0.00009318497,0.000236313,0.0001324016,0.00008460833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005408045,0.0004685581,0.001841983,0.0003448216,0.0002289392,0.0002401217,0.0001293752,0.07448285,0.02566129,0.00752197,0.04565987,0.8428793],"study_design_scores_gemma":[0.00002911925,0.00019569,0.001096442,0.00003703703,0.00003489076,0.0002513438,0.00004584406,0.972984,0.00714391,0.008502739,0.00964203,0.00003680176],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01237613,0.001340225,0.968201,0.0002132543,0.0003708065,0.0001973476,0.001895738,0.01341675,0.001988685],"genre_scores_gemma":[0.3292465,0.002079898,0.624928,0.0007911217,0.0005955369,0.0007155253,0.0214316,0.001582125,0.0186297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005890052,"threshold_uncertainty_score":0.01970416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0796470781317808,"score_gpt":0.3086133857295413,"score_spread":0.2289663075977605,"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."}}