{"id":"W4236114321","doi":"10.22215/etd/2017-12079","title":"Techniques for Enhancing the Computational Speed of Multiple Object Tracking","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Video tracking; Benchmark (surveying); Focus (optics); Overhead (engineering); Artificial intelligence; Speedup; Set (abstract data type); Real-time computing; Object (grammar); Computer vision; Data mining; Parallel computing","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":[0.001433225,0.000198107,0.0003575075,0.0001157949,0.0003435855,0.0002297211,0.001251766,0.0001572342,0.000006108399],"category_scores_gemma":[0.0006338429,0.0001415406,0.0002238714,0.00009815465,0.0000339099,0.000273461,0.00003610563,0.0001791955,0.000002172949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002116799,"about_ca_system_score_gemma":0.0002157159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001070661,"about_ca_topic_score_gemma":0.001114149,"domain_scores_codex":[0.9986092,0.0000892453,0.0004266114,0.0003650153,0.0003032792,0.0002066635],"domain_scores_gemma":[0.9968955,0.001426396,0.0006006866,0.0006170071,0.0004347692,0.00002563448],"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":[0.0000616464,0.00008105725,0.0006950357,0.0005216708,0.0001572057,0.000003293314,0.003158186,0.0004771573,0.01311698,0.01681737,0.0007134849,0.9641969],"study_design_scores_gemma":[0.000741066,0.0002341686,0.03925307,0.0008295344,0.00006153791,0.00001346305,0.0005008616,0.05644155,0.8394088,0.05675973,0.004858265,0.0008979445],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004160974,0.0001444215,0.9839489,0.0001110985,0.0008412881,0.0006356321,0.00001065964,0.0001803579,0.009966658],"genre_scores_gemma":[0.6839306,0.00001299259,0.3135364,0.00005722743,0.0001574577,0.00003880875,0.0001193021,0.00002284588,0.00212426],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.963299,"threshold_uncertainty_score":0.5771858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04296180239874257,"score_gpt":0.3597910808866947,"score_spread":0.3168292784879521,"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."}}