{"id":"W2472782738","doi":"10.1109/cvpr.2016.62","title":"A Deeper Look at Saliency: Feature Contrast, Semantics, and Beyond","year":2016,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Salient; Artificial intelligence; Context (archaeology); Semantics (computer science); Gaze; Variety (cybernetics); Contrast (vision); Feature (linguistics); Segmentation; Deep learning; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0008054743,0.00066616,0.0007117775,0.0008180646,0.000370453,0.001733571,0.0008761687,0.0008589256,0.002449789],"category_scores_gemma":[0.003555285,0.0003025162,0.0006003635,0.0006328271,0.001426687,0.005536629,0.001090984,0.00186664,0.0002810972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009194074,"about_ca_system_score_gemma":0.0004271517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004855479,"about_ca_topic_score_gemma":0.004356293,"domain_scores_codex":[0.9997835,0.00005954172,0.000006877287,0.00007057698,0.00004766032,0.00003189805],"domain_scores_gemma":[0.9990799,0.0005054686,0.0001067153,0.0001434763,0.00009536523,0.00006900336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003585476,0.0001350625,0.01217805,0.000568067,0.0002583926,0.0003818001,0.001233142,0.1480246,0.06451366,0.4703044,0.005279314,0.296765],"study_design_scores_gemma":[0.000009339898,0.0001947512,0.005758128,0.00009780547,0.00004759304,0.0002798106,0.0001852886,0.568953,0.008731773,0.4073139,0.008383853,0.00004473666],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1223178,0.007766924,0.8495446,0.006960693,0.0002066346,0.00004325064,0.0002501374,0.000563269,0.01234663],"genre_scores_gemma":[0.9192379,0.001891703,0.07466535,0.0003885397,0.0002292568,0.00001791545,0.0001404392,0.0001092063,0.003319668],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004855479,"threshold_uncertainty_score":0.009654462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007929065789871514,"score_gpt":0.2316497899769062,"score_spread":0.2237207241870347,"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."}}