{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007579615,0.001226488,0.0007811807,0.0006365438,0.0003879557,0.0008731306,0.002221069,0.000781715,0.003692376],"category_scores_gemma":[0.002670897,0.000515997,0.0004350388,0.0007080393,0.0003180584,0.001602129,0.001585957,0.001319995,0.001713414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009553868,"about_ca_system_score_gemma":0.001343444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01187212,"about_ca_topic_score_gemma":0.01916089,"domain_scores_codex":[0.9995945,0.00002859874,0.00001577396,0.000176796,0.0001315805,0.00005284095],"domain_scores_gemma":[0.9995909,0.00009286455,0.00003903422,0.0001430267,0.0000876081,0.00004652738],"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":[0.0006808418,0.0002849332,0.004008804,0.0001632803,0.0001530011,0.0001832355,0.0001329525,0.1323366,0.03849417,0.004308794,0.04240716,0.7768462],"study_design_scores_gemma":[0.00004751806,0.00006817425,0.001066388,0.000012294,0.00001517625,0.00007521471,0.00001321322,0.9812479,0.01124881,0.002255737,0.003930918,0.0000185994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05385647,0.000961734,0.8763619,0.0002189531,0.0002751903,0.0001874161,0.001250895,0.06282479,0.004062589],"genre_scores_gemma":[0.5056722,0.0004644042,0.4808793,0.0004837332,0.00008828712,0.0002418578,0.00449905,0.001651859,0.006019249],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01187212,"threshold_uncertainty_score":0.023606,"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."}}