{"id":"W4390577888","doi":"10.1109/tmm.2023.3345180","title":"Disentangled Representation Learning for Controllable Person Image Generation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Feature learning; Encoder; Artificial intelligence; Transformer; Component (thermodynamics); Segmentation; Pattern recognition (psychology); Representation (politics); Computer vision; Machine learning","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":[0.0005156408,0.0007193061,0.0005312131,0.0003444999,0.0001637176,0.0004276991,0.001174912,0.0007690144,0.003104708],"category_scores_gemma":[0.00172819,0.0003601518,0.0007124885,0.0003112588,0.0005768572,0.001092158,0.001069954,0.001404205,0.0009934362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004613831,"about_ca_system_score_gemma":0.0004408262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001625593,"about_ca_topic_score_gemma":0.002504577,"domain_scores_codex":[0.9995975,0.00009041595,0.0000116657,0.0001488659,0.0001007551,0.0000507429],"domain_scores_gemma":[0.9995481,0.0001775536,0.0000510337,0.0001194305,0.00006302134,0.00004081906],"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":[0.0003002585,0.000223929,0.001371625,0.0001870256,0.0001027217,0.0002612545,0.0001798852,0.4405108,0.05797292,0.02614676,0.00542047,0.4673223],"study_design_scores_gemma":[0.00001236137,0.00004867096,0.0001698981,0.000005859202,0.000009681439,0.00007195902,0.000009133872,0.9851479,0.007850404,0.005459195,0.00120659,0.000008394695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00959642,0.00009484957,0.9885717,0.00006740527,0.0000195149,0.00002520101,0.00007468751,0.0006975188,0.0008526454],"genre_scores_gemma":[0.5623228,0.0002978566,0.4277247,0.0004194797,0.00006226345,0.0001573287,0.001017319,0.0003718763,0.007626318],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003104708,"threshold_uncertainty_score":0.01038629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05382150064045672,"score_gpt":0.3332741873070718,"score_spread":0.2794526866666151,"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."}}