{"id":"W3081573667","doi":"10.1007/s11263-020-01371-6","title":"DeepVS2.0: A Saliency-Structured Deep Learning Method for Predicting Dynamic Visual Attention","year":2020,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Dropout (neural networks); Convolutional neural network; Pattern recognition (psychology); Frame (networking); Deep learning; Object (grammar); Kadir–Brady saliency detector; Computer vision; Motion (physics); Image (mathematics); Object detection; Machine learning","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":[0.0006284076,0.0001650862,0.0002390771,0.0002796446,0.0001403268,0.0003577399,0.0009353737,0.00008178255,0.00001363645],"category_scores_gemma":[0.0001132479,0.000147888,0.0003110212,0.0002536943,0.00001819011,0.001015229,0.0002362913,0.0003140307,0.00001008716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001001586,"about_ca_system_score_gemma":0.00004168922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002517842,"about_ca_topic_score_gemma":0.000002061062,"domain_scores_codex":[0.9977435,0.0001911217,0.0007263154,0.00031829,0.0008281244,0.0001926085],"domain_scores_gemma":[0.9980248,0.0001662531,0.0006992743,0.00008473972,0.0008669632,0.0001579255],"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":[0.0002495271,0.0001150057,0.0009079187,0.00002492531,0.00016606,0.00004560585,0.001150551,0.01748361,0.03276459,0.001636453,0.0001986679,0.9452571],"study_design_scores_gemma":[0.001207163,0.001476694,0.007246352,0.00007421857,0.00001755966,0.0002941712,0.00004810175,0.9848306,0.0007013103,0.001185684,0.002770823,0.000147274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06903572,0.00004858035,0.9254805,0.002700963,0.002489894,0.0001278491,0.000001254073,0.00009236907,0.00002289436],"genre_scores_gemma":[0.7058555,0.00001289163,0.2929026,0.0005499097,0.0006433291,0.000002231196,0.000007491704,0.00001196951,0.00001406046],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.967347,"threshold_uncertainty_score":0.6030699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01123918613067544,"score_gpt":0.3398915612615044,"score_spread":0.328652375130829,"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."}}