{"id":"W4383108465","doi":"10.1109/icra48891.2023.10160657","title":"SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded Network","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Iran Telecommunication Research Center","keywords":"Computer science; Artificial intelligence; Monocular; Depth map; Unsupervised learning; Inference; Ground truth; Pattern recognition (psychology); Computer vision; Image (mathematics)","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":[0.0002723993,0.0001552849,0.0001617696,0.0001200756,0.0002739354,0.0001713795,0.0002692031,0.00005239804,0.00001435971],"category_scores_gemma":[0.00001684809,0.0001330157,0.00004817315,0.0008690805,0.00004646516,0.001096276,0.00006106598,0.0001076822,0.00004226135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002840185,"about_ca_system_score_gemma":0.00004046236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006839404,"about_ca_topic_score_gemma":0.00002199549,"domain_scores_codex":[0.9987103,0.00004996002,0.0002319433,0.0003808042,0.0002447258,0.000382294],"domain_scores_gemma":[0.9994906,0.00007248475,0.00004233868,0.0002313181,0.00004484685,0.0001183706],"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":[0.000009129081,0.00001732187,0.001988781,0.00003318066,0.00002902706,0.00006901516,0.001437297,0.08132726,0.02962292,0.003157248,0.0002903463,0.8820185],"study_design_scores_gemma":[0.0002689741,0.00002138132,0.00244395,0.00003095596,0.000006692258,0.00004548255,0.00006107059,0.9835993,0.004911348,0.00816262,0.0002573793,0.0001908356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06959388,0.0001639739,0.9285221,0.0005586461,0.0001602564,0.0001571758,2.969755e-7,0.0003747542,0.0004689743],"genre_scores_gemma":[0.5946087,0.00004693214,0.4047996,0.0003975232,0.0000382121,0.000004556622,0.000002766848,0.00001153877,0.00009017097],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.902272,"threshold_uncertainty_score":0.5424224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03713493679006791,"score_gpt":0.2975626329668988,"score_spread":0.2604276961768309,"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."}}