{"id":"W2894545025","doi":"","title":"Deep Learning intra-image and inter-images features for Co-saliency detection.","year":2018,"lang":"en","type":"article","venue":"British Machine Vision Conference","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; Deep learning; Object detection; Image (mathematics); Pattern recognition (psychology)","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003626063,0.0001783717,0.0001987207,0.0001473669,0.0006234933,0.001109382,0.0004259235,0.0000946884,0.0001224519],"category_scores_gemma":[0.0002827578,0.0001963527,0.0000734702,0.0002618261,0.0002052858,0.0007981907,0.0001965934,0.0002509556,0.00004746928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002258613,"about_ca_system_score_gemma":0.0000232737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002477388,"about_ca_topic_score_gemma":0.0005609342,"domain_scores_codex":[0.9984213,0.0001238957,0.0002852704,0.0006300498,0.000229584,0.0003099529],"domain_scores_gemma":[0.9990586,0.00008892282,0.0001250835,0.0002334984,0.000357259,0.0001366401],"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":[0.00001803639,0.00004860784,0.0001371938,0.0000263263,0.000007775618,0.000006935007,0.0002056151,0.000001260226,0.01907231,0.001070197,0.000626963,0.9787788],"study_design_scores_gemma":[0.003430272,0.006027219,0.08266227,0.0004617697,0.00004186026,0.001734242,0.0003715976,0.7360296,0.1078184,0.01120933,0.04858752,0.001625951],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02231386,0.0002389844,0.973718,0.0003542244,0.000544577,0.0002675634,0.000007229375,0.0003548988,0.002200681],"genre_scores_gemma":[0.9850858,0.0001448979,0.01337227,0.000225156,0.0001398066,0.00003536143,0.000008902774,0.00001599315,0.0009717905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9771528,"threshold_uncertainty_score":0.9999276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01110870022174824,"score_gpt":0.2960805987948341,"score_spread":0.2849718985730858,"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."}}