{"id":"W4405786372","doi":"10.1109/iros58592.2024.10801790","title":"PhotoBot: Reference-Guided Interactive Photography via Natural Language","year":2024,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Photography; Natural (archaeology); Computational photography; Natural language; Computer graphics (images); Natural language processing; Artificial intelligence; Visual arts; Art; Image (mathematics); History; Image processing; Archaeology","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":[0.0006640529,0.0009361405,0.0006260987,0.0005781036,0.0004059738,0.001182038,0.002168141,0.000928048,0.01033855],"category_scores_gemma":[0.001754003,0.0005047883,0.0007414984,0.0002866687,0.001017648,0.002602907,0.002340658,0.0009456776,0.003263048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005566234,"about_ca_system_score_gemma":0.0005944088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002402728,"about_ca_topic_score_gemma":0.005042715,"domain_scores_codex":[0.9994047,0.0001632878,0.00002301155,0.0001892413,0.0001730644,0.00004665621],"domain_scores_gemma":[0.9995329,0.0002113526,0.00005372544,0.0001088965,0.0000564322,0.00003666445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007689707,0.0004004345,0.0009287572,0.001161495,0.0001144983,0.001160174,0.001819248,0.03852329,0.2468065,0.07317083,0.04443257,0.5907132],"study_design_scores_gemma":[0.0001289963,0.0003673937,0.001135289,0.0001265269,0.00004781174,0.001108355,0.0005144074,0.7534301,0.08481973,0.05479374,0.1033816,0.000146126],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005075778,0.0001915126,0.9798816,0.0001117156,0.00002797887,0.00009915086,0.0002065146,0.01188429,0.002521482],"genre_scores_gemma":[0.12065,0.0002380571,0.8699647,0.000234053,0.00003960254,0.0002973896,0.0008156902,0.001235427,0.006525105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01033855,"threshold_uncertainty_score":0.03458589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01753774276758273,"score_gpt":0.3033026274392986,"score_spread":0.2857648846717159,"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."}}