{"id":"W2259801182","doi":"10.1109/cvpr.2016.217","title":"A Hierarchical Deep Temporal Model for Group Activity Recognition","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":522,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Activity recognition; Baseline (sea); Dynamics (music); Aggregate (composite); Action (physics); Sequence (biology); Deep learning; Pattern recognition (psychology); Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003149211,0.00026161,0.0002733317,0.0001978185,0.0001594137,0.0002552228,0.0005569033,0.0003453119,0.00007326087],"category_scores_gemma":[0.00003716703,0.0002110752,0.0002739134,0.0000638042,0.00003994224,0.0005704674,0.0005801258,0.0003927672,0.0001300887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009117969,"about_ca_system_score_gemma":0.0001218372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001337659,"about_ca_topic_score_gemma":0.00005587147,"domain_scores_codex":[0.9982778,0.00007975272,0.0002669511,0.0008060775,0.0002504621,0.0003189741],"domain_scores_gemma":[0.998853,0.0001349499,0.0001919411,0.0005215451,0.0001599951,0.0001385835],"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":[0.00007258965,0.0002871212,0.00001119119,0.0001500049,0.00006019973,0.000003596203,0.0002106654,0.00007443913,0.000840954,0.01278666,0.002681951,0.9828206],"study_design_scores_gemma":[0.0003105385,0.00004337066,0.00003835117,0.00005994095,0.00001093471,0.000003721231,0.000001200364,0.5841101,0.0008447753,0.4140293,0.0002893886,0.000258348],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01049009,0.00000817348,0.9814552,0.001393044,0.0006264732,0.000678647,0.0000820614,0.0004559208,0.004810364],"genre_scores_gemma":[0.8103172,0.00002242573,0.186616,0.0005550436,0.0004802292,0.0005560361,0.0001679105,0.00002625998,0.00125891],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9825623,"threshold_uncertainty_score":0.8607397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06710757162622893,"score_gpt":0.2911387259577449,"score_spread":0.224031154331516,"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."}}