{"id":"W2292288263","doi":"10.1007/s11263-017-1013-y","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","year":2017,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":365,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Moment (physics); Action (physics); Action recognition; Sequence (biology); Frame (networking); Pattern recognition (psychology); Ranging; Sequence labeling; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002295232,0.00005689435,0.0001152271,0.0002443346,0.00005980142,0.000173031,0.0006873349,0.00002718339,0.00008365667],"category_scores_gemma":[0.00001741164,0.00005118857,0.00007245086,0.00003455368,0.0000218434,0.0007330199,0.0001335262,0.000110073,0.00003607525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000635923,"about_ca_system_score_gemma":0.00004191793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006034701,"about_ca_topic_score_gemma":0.000004947985,"domain_scores_codex":[0.9991053,0.00003043975,0.0003465963,0.00008385401,0.0003684275,0.00006540309],"domain_scores_gemma":[0.9988905,0.00004689597,0.0004572478,0.0001519657,0.000419903,0.0000335256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001814841,0.0009429416,0.007054058,0.00002868149,0.0003222597,0.000416797,0.0007684885,0.003150942,0.02328134,0.01187051,0.02140778,0.9305747],"study_design_scores_gemma":[0.006681409,0.001020293,0.4140552,0.001933092,0.00004470173,0.001133933,0.00005083923,0.4038622,0.01399831,0.02246195,0.1340946,0.0006633524],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2930673,0.00003840039,0.7007853,0.001642004,0.002837229,0.00006121281,0.00000374466,0.00001369302,0.001551121],"genre_scores_gemma":[0.9792399,0.00005008977,0.02021632,0.0001627146,0.0002761124,4.954672e-7,0.0000017061,0.00000324428,0.0000493843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9299114,"threshold_uncertainty_score":0.2087409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04994238637893542,"score_gpt":0.353276334976413,"score_spread":0.3033339485974775,"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."}}