{"id":"W3214009070","doi":"10.1109/iotdi54339.2022.00010","title":"DeepScale: Online Frame Size Adaptation for Multi-object Tracking on Smart Cameras and Edge Servers","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Server; Artificial intelligence; Video tracking; Edge computing; Convolutional neural network; Computation; Frame (networking); BitTorrent tracker; Real-time computing; Enhanced Data Rates for GSM Evolution; Testbed; Computer vision; Benchmark (surveying); Frame rate; Eye tracking; Video processing; Computer network; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001410191,0.0003936531,0.0005339333,0.0001708305,0.0002869251,0.0003379841,0.0008646637,0.0002499123,0.00004571188],"category_scores_gemma":[0.0006572317,0.0003875135,0.0002257658,0.0002504424,0.00004511781,0.0002378038,0.0008490184,0.0008247574,0.000003432733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000124296,"about_ca_system_score_gemma":0.0002096287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005561807,"about_ca_topic_score_gemma":0.0007779392,"domain_scores_codex":[0.9971957,0.0003808798,0.0004571693,0.001165772,0.0003903193,0.0004101405],"domain_scores_gemma":[0.9969496,0.00162654,0.0002810275,0.0008596519,0.0001618669,0.0001213103],"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":[0.0001747347,0.0009128772,0.01368597,0.0008208442,0.00038322,0.00005646077,0.006297364,0.05090609,0.000296617,0.007697823,0.0008054703,0.9179626],"study_design_scores_gemma":[0.001878069,0.0004528857,0.1184783,0.0001916022,0.0000526142,0.00001548559,0.0004634049,0.8636692,0.0005932875,0.006146255,0.00690302,0.001155896],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06379599,0.0002748638,0.9313768,0.0009279048,0.002013492,0.0008432441,0.00009490499,0.000394247,0.0002785742],"genre_scores_gemma":[0.2746691,0.0001027176,0.7229396,0.00126247,0.0001693315,0.0001578245,0.00009090482,0.00004212735,0.0005658758],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9168066,"threshold_uncertainty_score":0.9998577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1146159950879625,"score_gpt":0.3608745341324964,"score_spread":0.2462585390445338,"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."}}