{"id":"W4412444797","doi":"10.1109/mis.2025.3588759","title":"Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition","year":2025,"lang":"en","type":"article","venue":"IEEE Intelligent Systems","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"Russian Science Foundation","keywords":"Computer science; Pedestrian; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001966413,0.0002952782,0.0005054032,0.0003158027,0.0002842266,0.0004748388,0.0009174157,0.0002029112,0.000002537732],"category_scores_gemma":[0.000132606,0.0002753063,0.0002520438,0.000750404,0.00003597358,0.0005747593,0.00008861281,0.000188067,0.00009547411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001879747,"about_ca_system_score_gemma":0.0001552595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001798881,"about_ca_topic_score_gemma":0.00004019109,"domain_scores_codex":[0.9972563,0.0003175433,0.0007959405,0.0007266167,0.000318515,0.0005850202],"domain_scores_gemma":[0.997658,0.000737289,0.0002363241,0.0007781939,0.0004624053,0.0001278134],"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":[0.0002982848,0.000991728,0.007590296,0.00451581,0.001779156,0.0001687763,0.003535027,0.1346039,0.003662598,0.1782603,0.0882671,0.576327],"study_design_scores_gemma":[0.00120264,0.000276046,0.0001267994,0.001641068,0.0000912202,0.00005924829,0.0002027494,0.7168086,0.09652038,0.05724882,0.1246801,0.001142353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002375286,0.001691258,0.9856309,0.0006222263,0.007452849,0.0009749469,0.00005399125,0.0003979081,0.0008006646],"genre_scores_gemma":[0.9747869,0.0002839682,0.02199092,0.0003450309,0.000579873,0.0002593253,0.00005417401,0.00003230945,0.001667481],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9724116,"threshold_uncertainty_score":0.9999699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1044785828049656,"score_gpt":0.3292500610622297,"score_spread":0.2247714782572642,"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."}}