{"id":"W2799077596","doi":"10.1109/cvpr.2018.00783","title":"Going from Image to Video Saliency: Augmenting Image Salience with Dynamic Attentional Push","year":2018,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Salience (neuroscience); Visual attention; Artificial intelligence; Fixation (population genetics); Saliency map; Computer vision; Eye tracking; Attention network; Image (mathematics); Cognition; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003755349,0.0002362611,0.0001870152,0.0002114649,0.0004729945,0.0006087541,0.0008532653,0.00005389054,0.0004600289],"category_scores_gemma":[0.00005764388,0.0001981431,0.00008685968,0.0009207994,0.0001577454,0.001631075,0.0004041223,0.0001364106,0.002268542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001059943,"about_ca_system_score_gemma":0.00006914583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001641943,"about_ca_topic_score_gemma":0.0003289085,"domain_scores_codex":[0.9974826,0.00007760202,0.0003720771,0.0008982257,0.0006575619,0.0005119369],"domain_scores_gemma":[0.9987168,0.00005712178,0.0001326209,0.000583493,0.0002911877,0.0002187856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006724145,0.0003000299,0.00352279,0.00002235085,0.00006415461,0.00004745603,0.00147599,0.00002697769,0.9336857,0.01883059,0.003841947,0.03811474],"study_design_scores_gemma":[0.00300499,0.002492019,0.3066226,0.0004722065,0.00007420716,0.0001956511,0.0008403815,0.5471793,0.1128239,0.0123816,0.01125001,0.002663174],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2891563,0.000005279289,0.702038,0.001076649,0.0004799436,0.00017224,0.000004553924,0.0004380481,0.006629036],"genre_scores_gemma":[0.780318,0.000001401844,0.2166359,0.0009198152,0.0000900729,0.0000240172,0.000007376757,0.0000164485,0.001986944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8208618,"threshold_uncertainty_score":0.9985083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007646020957740102,"score_gpt":0.2678111350198347,"score_spread":0.2601651140620946,"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."}}