{"id":"W4366378394","doi":"10.1109/tmm.2023.3268369","title":"Discriminative Identity-Feature Exploring and Differential Aware Learning for Unsupervised Person Re-Identification","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Dalian Science and Technology Innovation Fund; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Liaoning Province; National Natural Science Foundation of China","keywords":"Discriminative model; Computer science; Artificial intelligence; Salient; Pattern recognition (psychology); Redundancy (engineering); Machine learning; Feature learning; Robustness (evolution); Identification (biology)","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":[0.0004315545,0.0001785958,0.000192939,0.000309688,0.0005240099,0.0002420877,0.0002982591,0.00008858995,0.00001000027],"category_scores_gemma":[0.00005408506,0.000175639,0.0001200518,0.0005426174,0.0000499662,0.001094467,0.00000443416,0.0003185486,0.00003443874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000411879,"about_ca_system_score_gemma":0.00002151491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002654577,"about_ca_topic_score_gemma":0.0000626578,"domain_scores_codex":[0.9985724,0.0001686298,0.0001702163,0.000512601,0.0002813797,0.0002947636],"domain_scores_gemma":[0.9988654,0.0005858688,0.00006944222,0.0002823354,0.0001022908,0.00009465282],"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":[0.00008346349,0.0001624329,0.0004276042,0.0002053222,0.0001420348,0.00001502882,0.02736863,0.008337482,0.02973958,0.0002146474,0.0002253545,0.9330784],"study_design_scores_gemma":[0.001593624,0.000190313,0.04586183,0.00011877,0.00006848869,0.000004986496,0.002946266,0.8906291,0.05738292,0.0004169572,0.000283018,0.0005037605],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1010159,0.00001814653,0.8959947,0.0006849068,0.001537731,0.0002944044,0.00001726096,0.0004242536,0.00001270814],"genre_scores_gemma":[0.9859859,0.0001274603,0.01283438,0.00002067517,0.00009628783,0.0002791364,0.00001975294,0.00002475682,0.0006116792],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9325746,"threshold_uncertainty_score":0.7162351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.11069083483818,"score_gpt":0.3299612520130516,"score_spread":0.2192704171748716,"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."}}