{"id":"W4385494459","doi":"10.1007/s13042-023-01927-1","title":"An improved deep network-based RGB-D semantic segmentation method for indoor scenes","year":2023,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; RGB color model; Segmentation; Feature (linguistics); Computer vision; Pattern recognition (psychology); Feature extraction; Convolutional neural network; Image segmentation; Semantics (computer science)","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":[0.002099594,0.0001132481,0.0001801373,0.000194402,0.000101189,0.0002366563,0.0004601339,0.0000509946,0.000004696631],"category_scores_gemma":[0.0002729148,0.00009909326,0.00008729599,0.0001905189,0.00001973783,0.0002169503,0.0000566694,0.0002331154,0.000001916497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002328834,"about_ca_system_score_gemma":0.000051812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002552136,"about_ca_topic_score_gemma":0.00002223476,"domain_scores_codex":[0.9986667,0.0003017084,0.00035277,0.0001753053,0.0003215557,0.0001819575],"domain_scores_gemma":[0.9984046,0.0006634209,0.0003706319,0.00009239434,0.000388124,0.00008084402],"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":[0.0001282836,0.00006629991,0.07314498,0.00002356177,0.0001587224,0.00003825654,0.0005836574,0.1548034,0.004643279,0.001175323,0.00008410963,0.7651501],"study_design_scores_gemma":[0.00106116,0.0003768867,0.01443679,0.00004172164,0.00001815783,0.0000614104,0.00003131278,0.9776157,0.001046254,0.003188739,0.002004501,0.0001174115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04037859,0.0002509063,0.9570785,0.001334122,0.0008006191,0.00007016918,0.000002187879,0.0000614583,0.00002341836],"genre_scores_gemma":[0.5734832,0.0001078022,0.4257284,0.0002259263,0.0003665756,0.000003331935,0.00001420196,0.0000127017,0.00005783049],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8228123,"threshold_uncertainty_score":0.4040906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01525735606037512,"score_gpt":0.3459064237830921,"score_spread":0.3306490677227169,"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."}}