{"id":"W2343467335","doi":"10.1007/s11042-016-4124-5","title":"Compressed-domain visual saliency models: a comparative study","year":2016,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Cisco Systems","keywords":"Computer science; Retargeting; Automatic summarization; Artificial intelligence; Computer vision; Domain (mathematical analysis); Video tracking; Pixel; Data compression; Object (grammar); Pattern recognition (psychology)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001574581,0.0001362001,0.0001667871,0.00007641635,0.000267658,0.0001413193,0.0003286848,0.00003905609,0.00001770228],"category_scores_gemma":[0.000006852846,0.00009403905,0.00003948359,0.0002829094,0.00008359487,0.0006478066,0.0001486281,0.0000650301,0.0001202246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002249249,"about_ca_system_score_gemma":0.00002021071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001485029,"about_ca_topic_score_gemma":0.00001773029,"domain_scores_codex":[0.9988206,0.00007861567,0.0002485603,0.0004446115,0.0002134082,0.0001941846],"domain_scores_gemma":[0.9992319,0.0001503325,0.0000808632,0.0003214859,0.00008570198,0.0001297481],"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":[0.00002613644,0.00310169,0.00302436,0.00001580122,0.0000789602,0.000003979634,0.008105335,0.00009918228,0.02704711,0.1415818,0.0007618023,0.8161539],"study_design_scores_gemma":[0.009353328,0.001796497,0.1085296,0.00009315187,0.00007256072,0.00004362961,0.006229845,0.7346282,0.005626539,0.08517955,0.0465131,0.001933992],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1041694,0.0000433524,0.8929816,0.0004151687,0.00006703979,0.000848319,0.00001630554,0.0001975391,0.001261264],"genre_scores_gemma":[0.9902892,0.00001774164,0.008593077,0.0000672493,0.00006684801,0.0007518061,0.000004248052,0.000006112064,0.0002037917],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8861197,"threshold_uncertainty_score":0.3834801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0628465635236268,"score_gpt":0.3286019874647187,"score_spread":0.265755423941092,"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."}}