{"id":"W4386392998","doi":"10.1007/s00521-023-08913-2","title":"Vision transformer with multiple granularities for person re-identification","year":2023,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Granularity; Discriminative model; Computer science; Transformer; Artificial intelligence; Benchmark (surveying); Pattern recognition (psychology); Feature extraction; Machine learning; Voltage; Engineering","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":[0.0003654343,0.00008731403,0.0001002094,0.00007824095,0.0004972787,0.0001719864,0.0002007104,0.00003133054,2.942639e-7],"category_scores_gemma":[0.0000154298,0.00007434522,0.00003622401,0.0004266442,0.00004112219,0.0001638233,0.00001286394,0.00007104161,0.000005468356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006540888,"about_ca_system_score_gemma":0.00001023566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001481739,"about_ca_topic_score_gemma":0.0000148344,"domain_scores_codex":[0.9992183,0.00003507667,0.0001316471,0.0003243629,0.0001095157,0.0001811338],"domain_scores_gemma":[0.9992439,0.0003551,0.00005334998,0.0002360285,0.0000697502,0.00004186343],"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":[0.00001781989,0.00005393445,0.006602947,0.0001424007,0.00001845922,0.000001187546,0.001902409,0.00282064,0.01192573,0.01806251,0.000649508,0.9578025],"study_design_scores_gemma":[0.0007588267,0.0001546887,0.1042929,0.00003742914,0.00001438862,0.00001597956,0.0003578631,0.8774887,0.004492811,0.003397418,0.008688658,0.0003003041],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08471497,0.00005123507,0.9125291,0.001738506,0.00005567111,0.0004024105,0.000006624125,0.0003951141,0.0001063729],"genre_scores_gemma":[0.9746628,0.00001161729,0.02493541,0.00008963626,0.00007494764,0.0001052086,0.0000277126,0.000009122381,0.00008357611],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9575021,"threshold_uncertainty_score":0.3824716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03952398071804249,"score_gpt":0.3236776671711854,"score_spread":0.2841536864531429,"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."}}