{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001411122,0.001328874,0.001632375,0.001764624,0.0008745543,0.0008557298,0.002581692,0.001240915,0.003430699],"category_scores_gemma":[0.003965949,0.0005255011,0.001474904,0.001851658,0.000837202,0.002442641,0.00199984,0.001829912,0.005268384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005967313,"about_ca_system_score_gemma":0.0008455898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003629257,"about_ca_topic_score_gemma":0.006201351,"domain_scores_codex":[0.9977452,0.0005385149,0.00007424645,0.0008795023,0.0005665157,0.0001960208],"domain_scores_gemma":[0.9973195,0.0004356473,0.0002336487,0.001284276,0.0006322264,0.00009468471],"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":[0.0006569337,0.0002883493,0.003822347,0.000189565,0.0001444806,0.0002068124,0.0003734573,0.04472072,0.03860487,0.007018558,0.01373258,0.8902413],"study_design_scores_gemma":[0.00003865119,0.0002180555,0.002795371,0.00003478114,0.00007952513,0.0006051815,0.0001987153,0.9260126,0.03960569,0.01677703,0.01354219,0.00009226996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01490512,0.000325187,0.9799203,0.00006923109,0.00007247701,0.00007404314,0.0002264819,0.003250752,0.001156343],"genre_scores_gemma":[0.3033112,0.0004536516,0.6811519,0.0004174769,0.000146252,0.0002294043,0.003661085,0.000967803,0.009661307],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003629257,"threshold_uncertainty_score":0.01147681,"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."}}