{"id":"W4383899685","doi":"10.1109/access.2023.3294247","title":"Compact Depth-Wise Separable Precise Network for Depth Completion","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Convolution (computer science); Scalability; Convolutional neural network; Margin (machine learning); Encoder; Stability (learning theory); Artificial intelligence; Enhanced Data Rates for GSM Evolution; Deep learning; Computer engineering; Algorithm; Artificial neural network; Machine learning","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":[0.0004039734,0.001031277,0.0006062583,0.0003504789,0.0002461819,0.0006474186,0.001623524,0.0007590092,0.002852086],"category_scores_gemma":[0.001497542,0.0005162127,0.0005153295,0.0004533385,0.0005515122,0.002265331,0.001204401,0.001906636,0.0007664436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009869871,"about_ca_system_score_gemma":0.001221585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009778883,"about_ca_topic_score_gemma":0.01769431,"domain_scores_codex":[0.9998005,0.00002217163,0.000009245622,0.00007006214,0.00006987251,0.00002813388],"domain_scores_gemma":[0.9996505,0.000123387,0.00004018827,0.00008888759,0.00007126826,0.00002577436],"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":[0.0001757357,0.00007960271,0.0005122721,0.000074462,0.00005011209,0.00008275059,0.00005444729,0.8592418,0.01407922,0.00861611,0.002387307,0.1146462],"study_design_scores_gemma":[0.000002728207,0.00001362883,0.00004125268,0.000002567652,0.000003309292,0.00001111034,0.000002154873,0.9963105,0.001714902,0.001613347,0.0002822278,0.000002308481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03138766,0.0003118443,0.9637685,0.000209366,0.00005655908,0.00004152491,0.0003254453,0.0022584,0.00164071],"genre_scores_gemma":[0.7297928,0.0004749887,0.2614374,0.000249106,0.00005090587,0.0001553108,0.001198667,0.0002507427,0.006390071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009778883,"threshold_uncertainty_score":0.01944393,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08914031691619162,"score_gpt":0.3901300141656101,"score_spread":0.3009896972494184,"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."}}