{"id":"W3157630927","doi":"10.32920/22734374.v1","title":"Motion Vector Extrapolation for Video Object Detection","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Object detection; Latency (audio); Motion vector; Optical flow; Motion estimation; Low latency (capital markets); Benchmark (surveying); 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":[0.000341489,0.000844999,0.0005211681,0.001108138,0.0002249063,0.0005863631,0.0009155758,0.000554249,0.005696808],"category_scores_gemma":[0.001724013,0.0003774142,0.0003952908,0.001154609,0.0002704732,0.0010409,0.0008400204,0.001061714,0.003301771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000741165,"about_ca_system_score_gemma":0.000644071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009231486,"about_ca_topic_score_gemma":0.009501111,"domain_scores_codex":[0.9997337,0.00002938166,0.000010342,0.00008821625,0.0001088702,0.00002938093],"domain_scores_gemma":[0.9997682,0.00006519787,0.00002568104,0.00005027164,0.00007238777,0.00001836278],"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":[0.0002563318,0.00008634907,0.0008986323,0.0001834195,0.00006264661,0.00011764,0.00004327155,0.06136263,0.05219426,0.009756278,0.02548762,0.849551],"study_design_scores_gemma":[0.00001595919,0.00005371977,0.001104661,0.00002974166,0.000011046,0.0000994931,0.00001701261,0.9536212,0.02211594,0.01107257,0.01184501,0.00001357482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0155555,0.002133896,0.9684076,0.0003899134,0.0002204996,0.0001209738,0.001101141,0.008087466,0.003982989],"genre_scores_gemma":[0.337025,0.002907438,0.6306633,0.0004699902,0.0002867177,0.0002557963,0.006134027,0.0009166103,0.02134121],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009231486,"threshold_uncertainty_score":0.01905769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05585239527241653,"score_gpt":0.3089934045694444,"score_spread":0.2531410092970279,"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."}}