{"id":"W3174397558","doi":"10.1609/aaai.v35i3.16282","title":"Patch-Wise Attention Network for Monocular Depth Estimation","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"SK Hynix","keywords":"Artificial intelligence; Computer science; Monocular; Merge (version control); Computer vision; Convolutional neural network; Benchmark (surveying); Depth map; Feature (linguistics); Pattern recognition (psychology); Image (mathematics); Geography","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":[0.0003564721,0.000163151,0.0001982284,0.00005156048,0.0002539204,0.000261323,0.0008712293,0.00005589777,0.00001842447],"category_scores_gemma":[0.0004847987,0.0001336348,0.0001452191,0.0005774145,0.00008744139,0.0005925444,0.0002591206,0.0001564976,0.00003315079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003556263,"about_ca_system_score_gemma":0.00008359375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007435695,"about_ca_topic_score_gemma":0.000006665204,"domain_scores_codex":[0.9984701,0.00001457915,0.0004301745,0.0004554964,0.0003205182,0.0003091508],"domain_scores_gemma":[0.9983818,0.00008248325,0.0003023381,0.0002779584,0.0008860078,0.00006944548],"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":[0.00001968911,0.00006643331,0.0002162434,0.00003022107,0.000008060015,3.929944e-7,0.0001985373,0.0007627652,0.01970522,0.5454277,0.0002424208,0.4333223],"study_design_scores_gemma":[0.00002374865,0.0000464128,0.0001997613,0.0001565362,0.000007257831,0.000002937917,0.0001171196,0.5561411,0.186287,0.2567221,0.0001850249,0.0001109667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01174972,0.00005250881,0.981737,0.003547283,0.000515784,0.0003381419,0.000002187212,0.00008307366,0.001974329],"genre_scores_gemma":[0.7985182,0.00003412885,0.2007727,0.0003230782,0.00007249384,0.0000348428,0.000001756275,0.00001037508,0.000232378],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7867686,"threshold_uncertainty_score":0.5449467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07354100882156708,"score_gpt":0.3248202371189472,"score_spread":0.2512792282973801,"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."}}