{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004161113,0.0001364095,0.0001547876,0.0001762609,0.0002493837,0.0003828178,0.0001681399,0.00006766493,0.0000334071],"category_scores_gemma":[0.00004281613,0.0001292095,0.0001605017,0.0003564577,0.00002692306,0.0006896874,7.946359e-7,0.0001997664,0.00009525662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006507267,"about_ca_system_score_gemma":0.00005095532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003133688,"about_ca_topic_score_gemma":0.00002795568,"domain_scores_codex":[0.9987882,0.0001528342,0.0001785269,0.0004508313,0.0002050038,0.0002245893],"domain_scores_gemma":[0.9989551,0.0006004136,0.00003702517,0.0002417727,0.00009684811,0.00006886673],"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":[0.00004961508,0.00009822098,0.00003332408,0.0000493193,0.000105513,0.00001936278,0.002331385,0.03500777,0.1811257,0.0001848483,0.001063731,0.7799312],"study_design_scores_gemma":[0.0005909271,0.0000922542,0.0000812001,0.00002147805,0.00002291659,0.000005427791,0.00005011666,0.9059048,0.0918995,0.00008708589,0.001105275,0.0001390598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004351746,0.0001304895,0.9910552,0.0008703973,0.002486948,0.0003732672,0.00001057073,0.0004875526,0.0002338476],"genre_scores_gemma":[0.8364776,0.00003706807,0.161718,0.0000703925,0.0002585241,0.0001750844,0.00001402617,0.0000223905,0.001226924],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.870897,"threshold_uncertainty_score":0.526901,"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."}}