{"id":"W2118527252","doi":"10.1109/cvpr.2013.343","title":"Recognize Human Activities from Partially Observed Videos","year":2013,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":203,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Science Foundation","keywords":"Subsequence; Activity recognition; Computer science; Artificial intelligence; Probabilistic logic; Pattern recognition (psychology); Longest common subsequence problem; Coding (social sciences); Machine learning; Algorithm; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00006679894,0.0001101265,0.0001186138,0.00005404237,0.0001732884,0.0004253428,0.0003555519,0.00005502156,0.00499591],"category_scores_gemma":[0.0000124439,0.00009698617,0.00006337332,0.00009810834,0.00002283355,0.001578843,0.00009963726,0.00009534469,0.002395826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000177912,"about_ca_system_score_gemma":0.00002064636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008486013,"about_ca_topic_score_gemma":0.0002344798,"domain_scores_codex":[0.9991043,0.0000570952,0.0001875038,0.0002880569,0.0001613078,0.0002016965],"domain_scores_gemma":[0.9993804,0.00008351445,0.00006490396,0.0003207784,0.00006178794,0.00008864254],"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":[0.000007494869,0.0003297857,0.00395259,0.00002062907,0.0001702184,0.00002067498,0.00184683,0.000008517552,0.3148831,0.02855754,0.102294,0.5479087],"study_design_scores_gemma":[0.001787064,0.0003216761,0.1060938,0.00009422461,0.00003357148,0.000009697063,0.0004870054,0.01711903,0.5931086,0.2483384,0.03122816,0.001378737],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8890957,0.00001266642,0.07840894,0.001027962,0.0003618333,0.0002093895,0.000002866471,0.0005523707,0.03032823],"genre_scores_gemma":[0.9849645,0.000004680224,0.009569238,0.001222013,0.0001790474,0.00006016931,0.00001473513,0.000007813742,0.003977743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5465299,"threshold_uncertainty_score":0.9983809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05268161478527138,"score_gpt":0.2420204123640053,"score_spread":0.1893387975787339,"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."}}