{"id":"W3031234741","doi":"10.1145/3318464.3384701","title":"SVQ++: Querying for Object Interactions in Video Streams","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Frame (networking); Object (grammar); Video tracking; Artificial intelligence; Computer vision; Video processing; Object detection; Frame rate; Pattern recognition (psychology)","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":[0.00008813229,0.00007406242,0.00009048117,0.0000607575,0.00007200127,0.00008527192,0.0004333013,0.00001595561,0.00003230459],"category_scores_gemma":[0.000184205,0.00007084222,0.00004483826,0.0003566385,0.000008590867,0.0002669554,0.0001203613,0.000147796,0.00009894757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003210902,"about_ca_system_score_gemma":0.00003436922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000911555,"about_ca_topic_score_gemma":0.0002198208,"domain_scores_codex":[0.9992893,0.00002692961,0.000161869,0.0002979279,0.00007314159,0.0001508018],"domain_scores_gemma":[0.9993452,0.0002655633,0.0000417051,0.0002426804,0.00003094515,0.00007391841],"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":[0.0000274407,0.0002729196,0.04628567,0.00007237626,0.00003727358,0.000005741279,0.007639412,0.0254569,0.01666052,0.3915186,0.006014712,0.5060084],"study_design_scores_gemma":[0.0002478368,0.00002961551,0.009682436,0.000007616046,0.00000165457,0.000001813592,0.00005420908,0.9789883,0.0009574866,0.001263684,0.008659962,0.0001053798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0307682,0.000007411032,0.9428496,0.02040439,0.00006609454,0.0002840743,0.000001842246,0.0002948479,0.005323476],"genre_scores_gemma":[0.8454751,7.277658e-7,0.1530912,0.001157348,0.00004843602,0.000117479,0.000003143899,0.000006245595,0.0001004054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9535314,"threshold_uncertainty_score":0.2888862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03883423857464274,"score_gpt":0.3277235061183179,"score_spread":0.2888892675436751,"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."}}