{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004219976,0.0004930879,0.0004124776,0.0004749308,0.0003704946,0.001094121,0.001652507,0.0001899258,0.00001907219],"category_scores_gemma":[0.00005427845,0.0004400609,0.00008803284,0.0006280317,0.001143127,0.001249785,0.00196212,0.001104234,0.00006755294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002220784,"about_ca_system_score_gemma":0.0001941283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001784807,"about_ca_topic_score_gemma":0.00001244897,"domain_scores_codex":[0.9964766,0.00001684612,0.0004605555,0.001661857,0.0007475599,0.0006365667],"domain_scores_gemma":[0.9984189,0.0001867694,0.0001595127,0.000829668,0.0001741489,0.0002309761],"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":[0.000001041671,0.000008580612,0.00000732099,0.00003763644,0.000005606201,0.00005902773,0.0003691493,0.0007027783,0.0004431908,0.007878672,0.0002202078,0.9902668],"study_design_scores_gemma":[0.0002221761,0.00008266015,0.00001274228,0.0007062914,0.000008951906,0.0003153305,0.00000224259,0.8270992,0.002392045,0.1497107,0.0187909,0.0006567832],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002408992,0.001159094,0.9887958,0.002963138,0.002923735,0.0002020428,0.00001127875,0.0002634866,0.003657339],"genre_scores_gemma":[0.03125599,0.0001686887,0.9633633,0.00183753,0.0008849669,0.000007709674,0.00000696905,0.00006459263,0.002410201],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.98961,"threshold_uncertainty_score":0.9999428,"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."}}