{"id":"W2914387319","doi":"10.1016/j.jvcir.2019.02.004","title":"ChaboNet : Design of a deep CNN for prediction of visual saliency in natural video","year":2019,"lang":"en","type":"article","venue":"Journal of Visual Communication and Image Representation","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Université de Bordeaux; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Residual; Convolutional neural network; Computer vision; Human visual system model; Coding (social sciences); Motion (physics); Affine transformation; Pattern recognition (psychology); Image (mathematics); Algorithm; 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":[0.0003019212,0.001043743,0.0006733615,0.0005195537,0.0003128746,0.0005711888,0.001997777,0.0008981948,0.004319234],"category_scores_gemma":[0.0007570696,0.0005534141,0.0004810461,0.0004140109,0.0002432108,0.0006924394,0.0006815899,0.0009889854,0.001128596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009808962,"about_ca_system_score_gemma":0.001302267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01708283,"about_ca_topic_score_gemma":0.0306259,"domain_scores_codex":[0.9998769,0.000006593002,0.000003555878,0.00004917744,0.00003045081,0.00003334176],"domain_scores_gemma":[0.9998502,0.00002472641,0.00001153878,0.00001121621,0.00007457486,0.00002767682],"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":[0.000755545,0.000405669,0.003930313,0.0003268105,0.0002985173,0.000315363,0.00007371094,0.194068,0.09058537,0.005792783,0.0357819,0.667666],"study_design_scores_gemma":[0.00001991624,0.00009250698,0.0004863918,0.000008666709,0.00002010632,0.00004136169,0.000006713714,0.9882382,0.008387666,0.001017557,0.001672575,0.000008402754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05373988,0.001429692,0.9270211,0.0005880502,0.000544016,0.0003699221,0.001286712,0.009297621,0.005723121],"genre_scores_gemma":[0.5908656,0.0007500576,0.3877263,0.0008169296,0.0002012788,0.0004907937,0.002737439,0.0004710653,0.01594058],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01708283,"threshold_uncertainty_score":0.03396684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0266897050275006,"score_gpt":0.3460803223231292,"score_spread":0.3193906172956286,"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."}}