{"id":"W3137858533","doi":"10.1109/tifs.2021.3107157","title":"Unsupervised and Self-Adaptative Techniques for Cross-Domain Person Re-Identification","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Information Forensics and Security","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Overfitting; Artificial intelligence; Machine learning; Identification (biology); Generalization; Task (project management); Feature (linguistics); Domain (mathematical analysis); Function (biology); Annotation; Adaptation (eye); Pattern recognition (psychology); Artificial neural network","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009658068,0.0002691477,0.0003154867,0.0002265097,0.0004486211,0.001191946,0.0002405661,0.0003153776,0.000003109427],"category_scores_gemma":[0.00001965746,0.0002797268,0.0001442416,0.0001929053,0.0000924417,0.001540113,0.00001513691,0.0004535611,0.000001493995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007491833,"about_ca_system_score_gemma":0.0001264834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005640262,"about_ca_topic_score_gemma":0.00005173461,"domain_scores_codex":[0.9985133,0.0001186669,0.0004872819,0.000400565,0.0002701735,0.0002100577],"domain_scores_gemma":[0.9984061,0.0001959084,0.0002878832,0.00047642,0.0005400395,0.00009362723],"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":[0.0001884435,0.0003899796,0.0001369528,0.002868601,0.0005634339,0.000005843959,0.1798255,0.003267603,0.0002660179,0.03126929,0.0005487028,0.7806696],"study_design_scores_gemma":[0.002928123,0.0007043509,0.005285155,0.0006613205,0.0002041987,0.00007353751,0.007294556,0.7644302,0.06569962,0.1417646,0.00856535,0.002388963],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04466384,0.00007169163,0.952738,0.0004177956,0.0006975421,0.0007067536,0.0001739732,0.0002813281,0.0002490444],"genre_scores_gemma":[0.8048546,0.0004250077,0.1941574,0.0002244484,0.00003140572,0.0002033409,0.00008242822,0.00001098209,0.00001038935],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7782807,"threshold_uncertainty_score":0.9999655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0262373163994332,"score_gpt":0.2951894032612501,"score_spread":0.2689520868618169,"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."}}