{"id":"W2737355296","doi":"10.1109/cvpr.2017.370","title":"Attentional Push: A Deep Convolutional Network for Augmenting Image Salience with Shared Attention Modeling in Social Scenes","year":2017,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Gaze; Salience (neuroscience); Computer science; Convolutional neural network; Artificial intelligence; Fixation (population genetics); Eye tracking; Computer vision; Visual attention; 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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0006156751,0.0001631783,0.0001744504,0.0001068345,0.001752051,0.0007395314,0.0006481908,0.00007288119,0.00003182474],"category_scores_gemma":[0.00004452403,0.0001498681,0.0001237414,0.00017784,0.00008911574,0.00184872,0.0001978974,0.0001125954,0.00002037388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008621872,"about_ca_system_score_gemma":0.00006235806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007294633,"about_ca_topic_score_gemma":0.0003126826,"domain_scores_codex":[0.9982095,0.00004716675,0.000344847,0.0005406732,0.0004045916,0.0004531964],"domain_scores_gemma":[0.9991395,0.00002789414,0.0002326753,0.0002773836,0.0002595558,0.00006291716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005608691,0.001079859,0.1395289,0.0002865086,0.0002087199,0.00003745217,0.0009991863,0.04303692,0.02046059,0.7387544,0.0027065,0.05234007],"study_design_scores_gemma":[0.001114319,0.00005926392,0.07454713,0.00005091432,0.000007648226,0.00001070494,0.0000586385,0.9171319,0.00003622858,0.006709069,0.00006015569,0.0002140289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1104596,0.00001248071,0.8867265,0.001220103,0.0003771699,0.0003057175,0.000003929662,0.0001131278,0.0007813581],"genre_scores_gemma":[0.9210223,0.000002006075,0.07804269,0.0001095787,0.0002862886,0.0001092229,0.00002441873,0.00001099659,0.0003924919],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.874095,"threshold_uncertainty_score":0.9995475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05677730376300189,"score_gpt":0.3115280189678631,"score_spread":0.2547507152048613,"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."}}