{"id":"W4313013512","doi":"10.1109/cvpr52688.2022.00716","title":"Part-based Pseudo Label Refinement for Unsupervised Person Re-identification","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":278,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Discriminative model; Computer science; Artificial intelligence; Smoothing; Context (archaeology); Cluster analysis; Similarity (geometry); Noise (video); Exploit; Machine learning; Pattern recognition (psychology); Feature (linguistics); Identification (biology); Code (set theory); Source code; Feature learning; Task (project management); Data mining; Image (mathematics)","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":[0.001518312,0.0003415011,0.0003897618,0.0003211492,0.0007749685,0.0005537642,0.0006607831,0.00008794845,0.0006485864],"category_scores_gemma":[0.0000254018,0.0003422551,0.0001471722,0.0003973841,0.00004786167,0.0003231951,0.0001690612,0.000358567,0.00007245215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008052568,"about_ca_system_score_gemma":0.00009866225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002867592,"about_ca_topic_score_gemma":0.00002388608,"domain_scores_codex":[0.9965976,0.0007031315,0.0005387986,0.001086178,0.0006517505,0.0004225563],"domain_scores_gemma":[0.9981435,0.0004028693,0.000316991,0.0006714729,0.0002954255,0.0001697465],"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":[0.0001048834,0.0004020462,0.0003086676,0.00008986588,0.00003330417,0.0000167803,0.0004792975,0.000170951,0.002269788,0.0003235237,0.01064674,0.9851542],"study_design_scores_gemma":[0.004531231,0.002642364,0.004220663,0.000239534,0.00003773866,0.00002691245,0.0002041547,0.9662951,0.004187609,0.002377238,0.01426967,0.0009678077],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07965615,0.0000454791,0.9099608,0.006020615,0.002678294,0.0007979684,0.0002432289,0.0002803469,0.0003171322],"genre_scores_gemma":[0.9566188,0.00008716028,0.03319826,0.008010814,0.0003686273,0.0006885924,0.0006625543,0.00004687432,0.0003183606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9841864,"threshold_uncertainty_score":0.999903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1351141458386117,"score_gpt":0.3274952700900095,"score_spread":0.1923811242513978,"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."}}