{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000309458,0.001221513,0.001022396,0.0008846742,0.0003269391,0.0004931086,0.001751991,0.001011505,0.00272843],"category_scores_gemma":[0.0009932294,0.0004007438,0.0006150792,0.0009677126,0.0003097063,0.001110435,0.0009666401,0.00101112,0.0006298261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001205591,"about_ca_system_score_gemma":0.0009618702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02782881,"about_ca_topic_score_gemma":0.02823917,"domain_scores_codex":[0.999715,0.00002735642,0.000009496697,0.0001089729,0.00006909735,0.00006999577],"domain_scores_gemma":[0.9997833,0.00007087969,0.00002474278,0.00002918035,0.0000733643,0.00001845472],"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":[0.0003223553,0.000173495,0.001471016,0.000145214,0.0001690205,0.00018804,0.00007968151,0.2022704,0.02684086,0.003207876,0.015258,0.7498741],"study_design_scores_gemma":[0.00001099726,0.00004047007,0.0006635177,0.000007322053,0.0000273823,0.00005560651,0.000009443055,0.991561,0.004348244,0.002152651,0.001114792,0.000008631724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06354776,0.004564425,0.917977,0.0005129136,0.0002964218,0.0001059909,0.000740184,0.007062761,0.005192494],"genre_scores_gemma":[0.7803073,0.001660964,0.2035332,0.0008517772,0.0003114264,0.0001335915,0.001851639,0.000321609,0.01102847],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02782881,"threshold_uncertainty_score":0.05533367,"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."}}