{"id":"W4386071639","doi":"10.1109/cvpr52729.2023.00148","title":"Good is Bad: Causality Inspired Cloth-debiasing for Cloth-changing Person Re-identification","year":2023,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":121,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Clothing; Computer science; Identification (biology); Debiasing; Artificial intelligence; Causality (physics); Causal inference; Discriminative model; Representation (politics); Inference; Machine learning; Psychology; Social psychology; Mathematics; Econometrics; Law","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":[0.003072107,0.0001678269,0.000220189,0.000304834,0.0003975229,0.0003635692,0.0005648685,0.00009572523,0.00001714146],"category_scores_gemma":[0.0002737233,0.0001645943,0.0001438806,0.001318501,0.0000283148,0.0005839003,0.0001270827,0.00009721723,0.0001258774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006372355,"about_ca_system_score_gemma":0.00005505956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001834339,"about_ca_topic_score_gemma":0.0000679476,"domain_scores_codex":[0.997996,0.0001599608,0.0003509916,0.0006503331,0.0003101835,0.0005325176],"domain_scores_gemma":[0.9984555,0.0004111945,0.0001559736,0.0007515262,0.0001417086,0.00008413099],"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":[0.00005530116,0.0002062313,0.0309164,0.0004410321,0.0002224922,0.00003753165,0.03351784,0.0004299977,0.03495544,0.1234458,0.0427048,0.7330672],"study_design_scores_gemma":[0.002356053,0.0002768044,0.2171461,0.0002137624,0.00006213313,0.00002644716,0.002983046,0.5393454,0.131233,0.03085968,0.07362805,0.001869492],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03367002,0.00007791224,0.9567025,0.004509535,0.001457982,0.0003657465,0.00001120498,0.00116339,0.002041761],"genre_scores_gemma":[0.8883427,0.00002901152,0.1057608,0.0009926646,0.0002403875,0.00007577903,0.00002396659,0.0000333731,0.004501236],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8546727,"threshold_uncertainty_score":0.671196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1007287493549492,"score_gpt":0.3521748838833079,"score_spread":0.2514461345283587,"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."}}