{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000991376,0.001237424,0.001032107,0.001096984,0.0004766427,0.001677712,0.002764629,0.001087897,0.007089783],"category_scores_gemma":[0.003066409,0.0005972426,0.0005721723,0.001377174,0.0006100258,0.002626532,0.002055786,0.001125161,0.001742679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009762141,"about_ca_system_score_gemma":0.000860104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01290829,"about_ca_topic_score_gemma":0.0180814,"domain_scores_codex":[0.9992907,0.00009433541,0.00004458768,0.0002046879,0.0003004728,0.00006529166],"domain_scores_gemma":[0.9992728,0.0003538144,0.00005755802,0.0001257386,0.0001329542,0.00005723517],"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":[0.002508388,0.0003635068,0.006517188,0.0007628726,0.0003253079,0.0007221927,0.000740143,0.05576844,0.08009457,0.02212186,0.1070892,0.7229863],"study_design_scores_gemma":[0.0001095572,0.0001374295,0.001535438,0.00002173048,0.0000303546,0.000200863,0.0001106936,0.9350964,0.0320041,0.01072789,0.01997496,0.00005048681],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05100855,0.0008605898,0.8468096,0.0004751782,0.0001768592,0.0004015675,0.007968755,0.08683278,0.00546614],"genre_scores_gemma":[0.3396341,0.0006758524,0.6333151,0.0004874849,0.0001178074,0.0004706373,0.01538583,0.00221707,0.007696022],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01290829,"threshold_uncertainty_score":0.0256663,"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."}}