{"id":"W4308237016","doi":"10.1109/icip46576.2022.9898010","title":"Back to Old Constraints to Jointly Supervise Learning Depth, Camera Motion and Optical Flow in a Monocular Video","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Image Processing (ICIP)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Optical flow; Artificial intelligence; Computer vision; Constraint (computer-aided design); Monocular; Computer science; Motion (physics); Interpretation (philosophy); Structure from motion; Deep learning; Brightness; Motion estimation; Image (mathematics); Mathematics; Optics; Physics; Geometry","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":[0.0004767345,0.0002224865,0.0002292126,0.0004701687,0.0002823743,0.000607285,0.0007767894,0.00003105668,0.0006714546],"category_scores_gemma":[0.0002418803,0.0002437643,0.00004675158,0.0005072967,0.00009204329,0.000826754,0.0005834182,0.0005966324,0.0001235888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002346935,"about_ca_system_score_gemma":0.0001177629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003089648,"about_ca_topic_score_gemma":0.00001393726,"domain_scores_codex":[0.9976736,0.0001222041,0.0003898114,0.0007689507,0.0006752144,0.0003702023],"domain_scores_gemma":[0.9991635,0.000060345,0.0000955399,0.0002186864,0.0002405715,0.0002213403],"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":[0.00008572735,0.0001729524,0.0008271024,0.00002760937,0.00001335041,0.0001163749,0.003549374,0.01174617,0.04880181,0.004541845,0.0003356123,0.9297821],"study_design_scores_gemma":[0.0006004158,0.0002027043,0.000962358,0.0001597767,0.000003307916,0.0000699104,0.0008202928,0.9912234,0.003127027,0.001252551,0.001233652,0.0003446227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03880807,0.00003650053,0.9439793,0.01004856,0.0006605843,0.000309254,0.000007739289,0.00009168134,0.006058322],"genre_scores_gemma":[0.8416342,0.000009338018,0.1545719,0.00276892,0.00005092794,0.00009367921,0.000009861787,0.00001967301,0.0008414485],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9794772,"threshold_uncertainty_score":0.9940418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04102845790298629,"score_gpt":0.3200933049682664,"score_spread":0.2790648470652801,"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."}}