{"id":"W4386245828","doi":"10.1007/s11263-023-01864-0","title":"Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-identification","year":2023,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Skeleton (computer programming); Artificial intelligence; Computer science; Identification (biology); Pattern recognition (psychology); Discriminative model; Flexibility (engineering); Consistency (knowledge bases); Topological skeleton; Construct (python library); Mathematics; Segmentation; Active shape model","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":[0.00219341,0.0001934044,0.0003998916,0.0005148918,0.0001456362,0.0004450795,0.001035535,0.00007401216,0.00001128258],"category_scores_gemma":[0.0001905203,0.0001454637,0.0003069558,0.0003843484,0.00004547612,0.000819959,0.0001104752,0.0003150435,0.00001338768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007544478,"about_ca_system_score_gemma":0.0001109696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005357359,"about_ca_topic_score_gemma":0.000002562905,"domain_scores_codex":[0.9975792,0.0003202328,0.0005637248,0.0003628799,0.0009191959,0.000254741],"domain_scores_gemma":[0.9969655,0.0009730397,0.0005566127,0.0001991739,0.001199558,0.0001060827],"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":[0.001551402,0.0002247288,0.003349646,0.00006195778,0.002783931,0.0003714149,0.004250655,0.0367141,0.01010413,0.003935583,0.00296594,0.9336865],"study_design_scores_gemma":[0.004643511,0.004686262,0.1022291,0.0004835865,0.0002446,0.0003966362,0.0001902442,0.8581178,0.005886686,0.003116104,0.01939754,0.0006078595],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.127567,0.000074658,0.8668215,0.00386585,0.001299024,0.0002310632,0.000003373875,0.00009449192,0.00004305073],"genre_scores_gemma":[0.7808416,0.00003331551,0.2181034,0.000197535,0.0006679259,0.00001985599,0.00001730746,0.00002080781,0.00009826021],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9330786,"threshold_uncertainty_score":0.5931839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06152453461712835,"score_gpt":0.3448180076763345,"score_spread":0.2832934730592062,"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."}}