{"id":"W2922263752","doi":"10.1016/j.neucom.2019.03.011","title":"Toward AI fashion design: An Attribute-GAN model for clothing match","year":2019,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Clothing; Computer science; Discriminator; Generator (circuit theory); Matching (statistics); Artificial intelligence; Similarity (geometry); Generative adversarial network; Collocation (remote sensing); Adversarial system; Generative grammar; Pattern recognition (psychology); Machine learning; Image (mathematics); Mathematics","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":[0.0006234269,0.000661472,0.0007086246,0.0005583602,0.0002335152,0.0008339138,0.001433254,0.001191382,0.003774384],"category_scores_gemma":[0.00117822,0.0005693666,0.0009628434,0.0006770981,0.0005013793,0.0008684356,0.0009153638,0.00172017,0.001395667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000570537,"about_ca_system_score_gemma":0.0004377313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00274639,"about_ca_topic_score_gemma":0.005272303,"domain_scores_codex":[0.9997416,0.00007113229,0.000007627171,0.00008853747,0.00005522287,0.0000359107],"domain_scores_gemma":[0.9997556,0.00009994712,0.00001984946,0.00005069752,0.00005124232,0.0000226603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001224277,0.0001211866,0.0009177746,0.0001012875,0.00008087196,0.00007420591,0.0000832208,0.7636546,0.00943659,0.02129992,0.006522617,0.1975854],"study_design_scores_gemma":[0.000002321765,0.000009548885,0.00005425705,0.000003520807,0.000004004701,0.00001424859,0.000004109134,0.9953035,0.0005461189,0.003472344,0.0005837905,0.00000232999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009320189,0.0002196995,0.9865964,0.000176011,0.00005511985,0.00003387882,0.0001057707,0.0005938157,0.002899105],"genre_scores_gemma":[0.5402585,0.0004631792,0.4421889,0.0006602293,0.00013075,0.0001413663,0.0007356163,0.0004193282,0.01500212],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003774384,"threshold_uncertainty_score":0.01262653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0666801175193587,"score_gpt":0.2795879814423403,"score_spread":0.2129078639229816,"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."}}