{"id":"W3043306352","doi":"10.1109/tip.2020.3007843","title":"An Object Context Integrated Network for Joint Learning of Depth and Optical Flow","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China","keywords":"Exploit; Computer science; Artificial intelligence; Context (archaeology); Optical flow; Pyramid (geometry); Object (grammar); Joint (building); Deep learning; Context model; Depth map; Unsupervised learning; Pattern recognition (psychology); Flow (mathematics); Machine learning; Computer vision; Image (mathematics); Mathematics; 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":[0.0001459192,0.0001374647,0.0002107031,0.00005838914,0.0002904104,0.0001876071,0.0001805541,0.00003732485,0.000005652075],"category_scores_gemma":[0.00003080699,0.0001254488,0.0000563444,0.0003467528,0.000084649,0.0009467655,0.000002823932,0.0002821539,0.000002260954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001635531,"about_ca_system_score_gemma":0.00007580552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003405931,"about_ca_topic_score_gemma":0.000003353147,"domain_scores_codex":[0.999001,0.00004201176,0.0002474449,0.0003541407,0.0001289355,0.0002264128],"domain_scores_gemma":[0.9994186,0.00007508964,0.00008281011,0.0001198678,0.000158366,0.0001453047],"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":[0.00004335116,0.00003915557,0.000005980182,0.00007429267,0.000006655653,0.000002098028,0.0009942862,0.01884766,0.02132775,0.00003116616,0.00001462473,0.958613],"study_design_scores_gemma":[0.0004416139,0.0002741458,0.00001998761,0.0001151807,0.00001169478,0.00000841138,0.000350698,0.9159713,0.08235367,0.0001159369,0.0002054965,0.0001318504],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008191724,0.0001415492,0.9979648,0.0005624876,0.00008634067,0.0001497523,0.000002330221,0.0001874971,0.00008604438],"genre_scores_gemma":[0.5582352,0.000009907831,0.4413984,0.0003060893,0.00002172679,0.000008550807,7.055891e-7,0.00001052303,0.000008968796],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9584811,"threshold_uncertainty_score":0.5115652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02675466751288624,"score_gpt":0.2883348237121275,"score_spread":0.2615801561992412,"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."}}