{"id":"W2772698361","doi":"10.1109/pacrim.2017.8121890","title":"Automatic image cropping based on bottom-up saliency and top-down semantics","year":2017,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cropping; Image (mathematics); Computer science; Semantics (computer science); Top-down and bottom-up design; Computer vision; Artificial intelligence; Image resolution; Agricultural engineering; Engineering; Agriculture; Software engineering; Geography; Programming language","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":[0.0002766251,0.0001187366,0.0001216446,0.0001006758,0.000583957,0.000860973,0.0005138012,0.00004762071,0.0000749185],"category_scores_gemma":[0.0001124672,0.00009815355,0.00005044616,0.00007936446,0.00007200036,0.0006248238,0.0001510215,0.0001060644,0.0001402593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001929519,"about_ca_system_score_gemma":0.00002757954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005243433,"about_ca_topic_score_gemma":0.00001046124,"domain_scores_codex":[0.999001,0.0000422336,0.000177405,0.0003235027,0.0002499377,0.0002059495],"domain_scores_gemma":[0.9989666,0.00003546676,0.0001142905,0.0007404297,0.00005307228,0.00009012983],"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":[0.00003021633,0.0007929475,0.01861666,0.0005016789,0.00005717612,0.0001490236,0.002055636,0.00008337054,0.06290618,0.2129591,0.007835905,0.6940121],"study_design_scores_gemma":[0.0004215799,0.0001423907,0.05074529,0.00004748488,0.000004946135,0.000009689148,0.00002478884,0.9426426,0.004344815,0.001090697,0.0003483672,0.0001774004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3233989,0.000005977724,0.6547035,0.003744194,0.0009700807,0.000160923,6.843389e-7,0.0003837084,0.01663207],"genre_scores_gemma":[0.9787769,0.00000270865,0.01918694,0.0006394102,0.0000322503,0.000004078177,4.57501e-7,0.000006203306,0.001351024],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9425592,"threshold_uncertainty_score":0.8302383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01922744407813361,"score_gpt":0.2974144239039,"score_spread":0.2781869798257664,"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."}}