{"id":"W4408564100","doi":"10.1109/tetci.2025.3547851","title":"Latent Object Embedding for Self-Supervised Monocular Depth Estimation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Monocular; Artificial intelligence; Embedding; Object (grammar); Computer vision; Computer science; Estimation; Pattern recognition (psychology); Engineering","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":[0.0002267346,0.0001631835,0.0001596108,0.0004297105,0.0002593274,0.0001061152,0.0004343376,0.00005360846,0.000008340356],"category_scores_gemma":[0.00002423014,0.0001799978,0.0001051704,0.0007002763,0.00002613655,0.0004332418,0.000007023029,0.0002118026,0.00001089886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001725856,"about_ca_system_score_gemma":0.0001079505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001152854,"about_ca_topic_score_gemma":0.000009094244,"domain_scores_codex":[0.9986429,0.00004693069,0.0004114778,0.0004304429,0.0002288386,0.0002394037],"domain_scores_gemma":[0.9991109,0.0003703477,0.00006174804,0.0002540177,0.000157587,0.00004534162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005349512,0.00006969859,0.00001299076,0.00001991177,0.00001212944,0.000001311208,0.0002762594,0.6527714,0.00001563319,0.01195451,0.00001233427,0.3348485],"study_design_scores_gemma":[0.0001785152,0.00003465194,0.00009850976,0.0001123195,0.000007144731,0.000002175037,0.00003937726,0.9371614,0.004163698,0.05779325,0.0002543893,0.0001545738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006077609,0.00006281022,0.9959832,0.001615164,0.0009833364,0.0003291455,0.000002479448,0.0002089201,0.0002071644],"genre_scores_gemma":[0.4313198,0.00002395798,0.5681183,0.0003664522,0.0000126813,0.00005206225,0.000002114261,0.000006212092,0.00009842809],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.430712,"threshold_uncertainty_score":0.7340099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03150151107509905,"score_gpt":0.3529864184218318,"score_spread":0.3214849073467327,"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."}}