{"id":"W4406864303","doi":"10.1016/j.neucom.2025.129534","title":"ATPTrack: Visual tracking with alternating token pruning of dynamic templates and search region","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Hong Kong Polytechnic University; Columbus State University","keywords":"Security token; Pruning; Computer science; Template; Eye tracking; Tracking (education); Artificial intelligence; Pattern recognition (psychology); Computer vision; Biology; Computer network","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":[],"consensus_categories":[],"category_scores_codex":[0.0007555325,0.0001649568,0.0002635036,0.00023099,0.000245061,0.0001907231,0.0004351778,0.00004739806,2.70097e-7],"category_scores_gemma":[0.00008753374,0.0001497991,0.00003956483,0.000628043,0.00006231344,0.0003353212,0.0003384508,0.000288273,5.038997e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002148143,"about_ca_system_score_gemma":0.00006318939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004516347,"about_ca_topic_score_gemma":0.000008710901,"domain_scores_codex":[0.9983768,0.0002132128,0.00033043,0.000498489,0.000239558,0.0003414698],"domain_scores_gemma":[0.9986798,0.0007175553,0.0001626871,0.0002693752,0.0001232464,0.00004740263],"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":[0.00001968433,0.00004393395,0.1383809,0.0002189273,0.0000405138,0.00009032736,0.00117955,0.005078481,0.009792941,0.002471824,0.000004193262,0.8426787],"study_design_scores_gemma":[0.0006346229,0.000188862,0.2291358,0.0007047217,0.00001051283,0.0001473191,0.0001090724,0.7563865,0.01192448,0.0004637505,0.00005456308,0.0002397717],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.588879,0.00008791356,0.4101824,0.000179792,0.00008931617,0.0001006685,1.088516e-7,0.0001095085,0.000371282],"genre_scores_gemma":[0.9279141,0.00001202966,0.07188647,0.0001197327,0.00002841912,0.000001923511,5.040656e-7,0.00001302599,0.00002380533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8424389,"threshold_uncertainty_score":0.6108629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01676145472659725,"score_gpt":0.317196366016073,"score_spread":0.3004349112894758,"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."}}