{"id":"W4400391233","doi":"10.1016/j.imavis.2024.105160","title":"GDM-depth: Leveraging global dependency modelling for self-supervised indoor depth estimation","year":2024,"lang":"en","type":"article","venue":"Image and Vision Computing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Ministry of Education of the People's Republic of China; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Ground truth; Feature (linguistics); Unary operation; Data mining; Machine learning; Pattern recognition (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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005153512,0.0002491305,0.0002299584,0.0001435948,0.0004729524,0.001227167,0.0004012747,0.00006141425,0.000003314124],"category_scores_gemma":[0.00006641941,0.0002327463,0.0001080399,0.0004624142,0.0000265656,0.001795528,0.0004059812,0.0001985492,0.00002622194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008117053,"about_ca_system_score_gemma":0.0000774585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001431261,"about_ca_topic_score_gemma":0.00000122612,"domain_scores_codex":[0.9980295,0.0000526677,0.0004058841,0.0007680406,0.0003014372,0.0004424142],"domain_scores_gemma":[0.9989931,0.0003519622,0.00007693152,0.0003028309,0.0001316227,0.000143571],"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":[0.000004990427,0.00002685193,0.0001037351,0.000129502,0.00001217673,0.00002393504,0.0007023828,0.0078424,0.0004769622,0.003270862,0.000188714,0.9872175],"study_design_scores_gemma":[0.000466764,0.0000589585,0.0001455302,0.0003550581,0.00001331683,0.00006993249,0.00006004867,0.9866446,0.0004648175,0.01034664,0.001092674,0.0002816329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01077653,0.001258523,0.9848899,0.0005599462,0.0006115673,0.0002919218,0.00000277607,0.0008867243,0.0007221579],"genre_scores_gemma":[0.4786953,0.00002750777,0.5209577,0.0001924576,0.00009359434,0.000003055365,0.000004146972,0.00001367949,0.00001257295],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9869359,"threshold_uncertainty_score":0.9998097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02517563298204604,"score_gpt":0.3412107901119456,"score_spread":0.3160351571298995,"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."}}