{"id":"W2854772608","doi":"10.1007/s13319-018-0181-z","title":"Perceptually Improved 3D Object Representation Based on Guided Adaptive Weighting of Feature Channels of a Visual-Attention Model","year":2018,"lang":"en","type":"article","venue":"3D Research","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Salient; Computer science; Artificial intelligence; Human visual system model; Computer vision; Feature (linguistics); Weighting; Representation (politics); Visualization; Pattern recognition (psychology); Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002321317,0.0005919571,0.0005883923,0.0004935153,0.0001852779,0.0005889561,0.0008377283,0.0005106917,0.001790041],"category_scores_gemma":[0.0007161177,0.0002825271,0.0006343031,0.0005155735,0.000278402,0.000764095,0.0007455347,0.000541397,0.0003889007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004111724,"about_ca_system_score_gemma":0.0004200183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003965542,"about_ca_topic_score_gemma":0.003760839,"domain_scores_codex":[0.9998651,0.00002488428,0.000005590824,0.00003870419,0.00004676191,0.00001905995],"domain_scores_gemma":[0.9997916,0.00004973893,0.00002071253,0.00004743584,0.000064154,0.00002646378],"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":[0.0004427067,0.0001495155,0.0008591994,0.0002188804,0.0001358067,0.0001656954,0.0001550662,0.2830772,0.3273234,0.02464556,0.00423056,0.3585964],"study_design_scores_gemma":[0.000004693717,0.0000248761,0.0002336667,0.00000273215,0.00001272227,0.00003300246,0.000005184482,0.9909313,0.006301556,0.001937999,0.0005043613,0.000007893977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02497561,0.0001976388,0.9731284,0.0000995529,0.00004955297,0.00002165922,0.00006541977,0.0004715473,0.0009906663],"genre_scores_gemma":[0.6338652,0.0004891223,0.3623718,0.0001814538,0.00006665758,0.0000570574,0.000249342,0.000193964,0.002525422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003965542,"threshold_uncertainty_score":0.00788492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1034101489527611,"score_gpt":0.4084781755637722,"score_spread":0.3050680266110111,"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."}}