{"id":"W4390413994","doi":"10.1016/j.cviu.2023.103905","title":"IGMG: Instance-guided multi-granularity for domain generalizable person re-identification","year":2023,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Computer science; Granularity; Artificial intelligence; Machine learning; Overfitting; Embedding; Source code; Robustness (evolution); Identification (biology); Generalization; Normalization (sociology); Feature (linguistics); Benchmark (surveying); Artificial neural 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":[0.001556888,0.0002042424,0.0002649312,0.0002978274,0.000634904,0.0008335328,0.0004169001,0.00008845971,0.000003909783],"category_scores_gemma":[0.00004927737,0.0001915398,0.0001125418,0.0006737749,0.00007874848,0.0008691514,0.0001874199,0.000119875,0.00001611081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001317356,"about_ca_system_score_gemma":0.00002758124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001142278,"about_ca_topic_score_gemma":0.00001352816,"domain_scores_codex":[0.9981666,0.0001753163,0.0003227407,0.0006741713,0.0002516101,0.000409542],"domain_scores_gemma":[0.9989415,0.0002362781,0.0001320975,0.0004757041,0.00009652255,0.0001179247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001739413,0.0005166146,0.00960389,0.001280624,0.0002852489,0.0002670467,0.02444317,0.001949247,0.1290937,0.5338231,0.1351371,0.1634262],"study_design_scores_gemma":[0.001870126,0.0001062518,0.006455511,0.0001030571,0.000008105607,0.00001811845,0.0004433448,0.9540744,0.001199522,0.03154961,0.003778764,0.0003931548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01027542,0.00008257549,0.985993,0.001777472,0.0009084137,0.0003534633,0.000007341657,0.0004574109,0.0001449344],"genre_scores_gemma":[0.3356778,0.0001027058,0.6634578,0.0003506908,0.0001363224,0.00001935717,0.00003123859,0.00002398951,0.000200094],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9521252,"threshold_uncertainty_score":0.8037776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.192780774647972,"score_gpt":0.3740160916887619,"score_spread":0.1812353170407899,"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."}}