{"id":"W2938050891","doi":"10.1109/cvpr.2019.01015","title":"Action Recognition From Single Timestamp Supervision in Untrimmed Videos","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Engineering and Physical Sciences Research Council","keywords":"Timestamp; Computer science; Discriminative model; Classifier (UML); Artificial intelligence; Action recognition; Sampling (signal processing); Machine learning; Action (physics); Pattern recognition (psychology); Computer vision; Real-time computing; Class (philosophy)","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":[0.001051052,0.001472107,0.001205648,0.001098526,0.0003052281,0.0009475364,0.001626359,0.001162015,0.002710383],"category_scores_gemma":[0.005640015,0.0004519831,0.0006024646,0.0008397159,0.0006817121,0.001683024,0.001225905,0.00148766,0.00246647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006474309,"about_ca_system_score_gemma":0.0009412268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007957891,"about_ca_topic_score_gemma":0.01684078,"domain_scores_codex":[0.9986804,0.0002010048,0.00006548149,0.0005541661,0.0003463842,0.0001524799],"domain_scores_gemma":[0.9977561,0.0005752072,0.0002969202,0.0007578132,0.0004599505,0.0001541413],"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":[0.001164218,0.0004293912,0.00880739,0.0004247601,0.0001627625,0.0003950542,0.0002031357,0.04231382,0.09474694,0.001100252,0.01806555,0.8321868],"study_design_scores_gemma":[0.00004714176,0.0004835245,0.01881875,0.00009040705,0.00007042782,0.0006501196,0.0001832251,0.8879967,0.07844648,0.004349966,0.008803524,0.00005965269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2500698,0.001972723,0.704419,0.000396797,0.0005402899,0.0003343795,0.004716087,0.03062594,0.006924977],"genre_scores_gemma":[0.7424425,0.00058749,0.2396882,0.0002418332,0.0002087855,0.0001714761,0.01022625,0.0004696693,0.005963929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007957891,"threshold_uncertainty_score":0.01582313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07993559894020286,"score_gpt":0.2794343149996715,"score_spread":0.1994987160594687,"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."}}