{"id":"W4402997546","doi":"10.1007/978-3-031-72920-1_7","title":"Watch Your Steps: Local Image and Scene Editing by Text Instructions","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute; Centre for Social Innovation; York University; University of Toronto","funders":"","keywords":"Computer science; Image editing; Image (mathematics); Computer graphics (images); Computer vision; Artificial intelligence; Information retrieval; Natural language processing","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":[0.0002594156,0.001289969,0.0005064901,0.001005546,0.0005279719,0.001330541,0.001216467,0.0007336445,0.2385844],"category_scores_gemma":[0.001273621,0.0005660011,0.0005430151,0.000646956,0.0002886345,0.001349411,0.001130646,0.001028165,0.1038049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002483568,"about_ca_system_score_gemma":0.0002315641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001191708,"about_ca_topic_score_gemma":0.002556243,"domain_scores_codex":[0.9998684,0.00001239124,0.000006856312,0.00003296938,0.00005958426,0.00001976861],"domain_scores_gemma":[0.9993324,0.0001903273,0.00002277415,0.0001887157,0.0001697032,0.00009605416],"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":[0.0003492639,0.00008550277,0.000199983,0.0002779825,0.00002483119,0.000295779,0.0002381959,0.001845796,0.06754285,0.005528195,0.313943,0.6096686],"study_design_scores_gemma":[0.00009607591,0.0001936091,0.001877894,0.0001388008,0.00008028545,0.00114052,0.000299493,0.03473121,0.09651484,0.01091134,0.8538979,0.0001181082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008502858,0.0007156247,0.7169176,0.0009043342,0.001775529,0.0004483359,0.002052417,0.09390585,0.1747774],"genre_scores_gemma":[0.05696119,0.001071664,0.5717419,0.0007356114,0.0006320609,0.0002425387,0.003296398,0.04043463,0.324884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2385844,"threshold_uncertainty_score":0.7981443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01141436307618282,"score_gpt":0.2648074394066484,"score_spread":0.2533930763304655,"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."}}