{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001297537,0.0001236895,0.0001028127,0.0002059444,0.00005098491,0.0003465464,0.0005656689,0.00004884641,0.0001939786],"category_scores_gemma":[0.00001531583,0.00009008546,0.00009435832,0.0007552483,0.00003872887,0.000661179,0.0001321064,0.0002389872,0.0002646455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003933385,"about_ca_system_score_gemma":0.0000376381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000113751,"about_ca_topic_score_gemma":0.000005665951,"domain_scores_codex":[0.9990532,0.00003498846,0.0001686536,0.0003624817,0.0002031653,0.0001775597],"domain_scores_gemma":[0.9994041,0.00007156851,0.00002951238,0.0003634981,0.00007909751,0.00005227166],"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":[0.00001036086,0.0000759414,0.00002573954,0.00005704041,0.00007588925,0.0001051364,0.00257132,8.646579e-8,0.3920453,0.08006316,0.01445541,0.5105146],"study_design_scores_gemma":[0.00008678121,0.00005955939,0.0002735223,0.00005753027,0.00000708884,0.00006835639,0.0001460736,0.06726861,0.9000717,0.003995039,0.0276811,0.0002846751],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001948316,0.0009838567,0.9397085,0.0007477241,0.0005373858,0.0001928326,0.000002932789,0.002173811,0.0537047],"genre_scores_gemma":[0.9750129,0.000033357,0.02034167,0.0004628252,0.00003930863,0.00002887736,0.00000707165,0.000007952099,0.004066037],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9730646,"threshold_uncertainty_score":0.3673579,"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."}}