{"id":"W4286970487","doi":"10.48550/arxiv.2109.09923","title":"AutoPhoto: Aesthetic Photo Capture using Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Reinforcement learning; Computer science; Heuristics; Motion capture; Process (computing); Estimator; Artificial intelligence; Pipeline (software); Metric (unit); Computer vision; Robot; Human–computer interaction; Motion (physics); Engineering; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005330482,0.0005836859,0.0005346279,0.0003657798,0.0002730291,0.0005224648,0.001366492,0.0005677723,0.003121757],"category_scores_gemma":[0.00148295,0.0003936208,0.0004209444,0.0001903155,0.0006221575,0.001001008,0.001108273,0.0008318099,0.0005726028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006629912,"about_ca_system_score_gemma":0.0004781646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003400956,"about_ca_topic_score_gemma":0.005907178,"domain_scores_codex":[0.999777,0.00004063225,0.00000554604,0.00008708656,0.0000603749,0.00002929669],"domain_scores_gemma":[0.9995064,0.00018838,0.00007538627,0.0000972331,0.00006801826,0.00006461129],"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":[0.0003324945,0.000409937,0.004230501,0.0002127281,0.0001069359,0.0003117289,0.000332298,0.4358494,0.06423023,0.01083673,0.007988221,0.4751588],"study_design_scores_gemma":[0.00001497601,0.00005474366,0.0005813711,0.000006594168,0.000006003199,0.00005058425,0.00001316366,0.9887646,0.005170415,0.004003341,0.001324168,0.000009942009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05609789,0.0002731311,0.9336783,0.0001926231,0.00006072663,0.0001674278,0.00008756719,0.004691638,0.004750555],"genre_scores_gemma":[0.7134146,0.0001528536,0.2806464,0.0001653889,0.0000337332,0.0001340648,0.0001494951,0.0003295756,0.004973772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003400956,"threshold_uncertainty_score":0.01044333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0730158786417651,"score_gpt":0.2103330890919585,"score_spread":0.1373172104501934,"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."}}