{"id":"W3000529389","doi":"10.1109/wacv45572.2020.9093606","title":"Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Adaptability; Artificial intelligence; Cluster analysis; Machine learning; Identification (biology); Robustness (evolution); Scalability; Annotation; Unsupervised learning; Benchmark (surveying); Adaptation (eye); Domain (mathematical analysis); Pattern recognition (psychology)","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":[0.0009833496,0.0003642084,0.0005206501,0.0001443867,0.0001018523,0.0002087434,0.0006325058,0.0002712351,0.00005283155],"category_scores_gemma":[0.00004120595,0.0003619577,0.0001147577,0.0001276801,0.00003791949,0.0001667121,0.001134878,0.0004494121,0.00003581705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001388438,"about_ca_system_score_gemma":0.00004763477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001922539,"about_ca_topic_score_gemma":0.0004698768,"domain_scores_codex":[0.9971378,0.0004983803,0.0004081011,0.001171132,0.0003693307,0.0004152053],"domain_scores_gemma":[0.9987704,0.000256214,0.0001343946,0.0006659772,0.00001459481,0.00015848],"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":[0.0002459006,0.0005351435,0.01320472,0.001247425,0.0002821557,0.0006594814,0.05669832,0.1256044,0.005063431,0.0002998997,0.0000693699,0.7960897],"study_design_scores_gemma":[0.0004436171,0.00007581966,0.009974394,0.0001385996,0.00001447653,0.00002410829,0.0005727806,0.9843525,0.001590357,0.001592204,0.0006399298,0.0005812534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04508591,0.0003861981,0.9518919,0.001398052,0.0002484934,0.0003859267,0.00001126766,0.0001636743,0.0004285552],"genre_scores_gemma":[0.6426536,0.0001297188,0.3567567,0.0002576208,0.00006262267,0.000089782,0.000009572558,0.0000235039,0.000016865],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.858748,"threshold_uncertainty_score":0.9998832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04602381814675512,"score_gpt":0.2594556655881834,"score_spread":0.2134318474414283,"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."}}