{"id":"W4387604812","doi":"10.2139/ssrn.4601111","title":"Deep Learning and Multi-Modal Fusion for Real-Time Multi-Object Tracking: Algorithms, Challenges, Datasets, and Comparative Study","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Modal; Computer science; Artificial intelligence; Fusion; Tracking (education); Deep learning; Object (grammar); Algorithm; Video tracking; Computer vision; Machine learning; 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":[0.006464338,0.001655845,0.001773182,0.002123135,0.0006744441,0.002216215,0.0017988,0.002120124,0.00215951],"category_scores_gemma":[0.01094285,0.0005856217,0.001245716,0.003484833,0.000728039,0.003493921,0.00239117,0.002211031,0.0008130811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001317539,"about_ca_system_score_gemma":0.001824258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01240469,"about_ca_topic_score_gemma":0.009249344,"domain_scores_codex":[0.9975343,0.0007866012,0.0001609855,0.0005404864,0.000710541,0.000267109],"domain_scores_gemma":[0.9951426,0.002496961,0.0002798488,0.001008308,0.0009137763,0.0001584964],"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":[0.00207997,0.001092109,0.01216821,0.00105013,0.0008030029,0.00008695438,0.0001286889,0.1616638,0.007071741,0.007023324,0.01194167,0.7948905],"study_design_scores_gemma":[0.00005954813,0.0003154819,0.007088375,0.0001522214,0.0002228425,0.0001460273,0.0001385011,0.9666927,0.008179151,0.01218799,0.00475604,0.00006109204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.2137322,0.01959595,0.7499238,0.001646583,0.0006351983,0.0002949721,0.004067671,0.003817938,0.006285604],"genre_scores_gemma":[0.7506831,0.005051095,0.2284637,0.0003137603,0.0002202974,0.0002210647,0.0109142,0.0002265548,0.003906209],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01240469,"threshold_uncertainty_score":0.03418708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1186940898425711,"score_gpt":0.3808986459174012,"score_spread":0.2622045560748301,"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."}}