{"id":"W2962865320","doi":"10.1109/access.2019.2930293","title":"SKFlow: Optical Flow Estimation Using Selective Kernel Networks","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":7,"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":"Computer science; Optical flow; Kernel (algebra); Convolutional neural network; Artificial intelligence; Pyramid (geometry); Aggregate (composite); Feature (linguistics); Convolution (computer science); Receptive field; Pattern recognition (psychology); Field (mathematics); Feature extraction; Information flow; Artificial neural network; Computer vision; Image (mathematics); Mathematics","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":[0.0001181348,0.0001101072,0.0001298378,0.00007058832,0.00009137193,0.0003464886,0.0007002291,0.00004489199,0.0000167539],"category_scores_gemma":[0.00002613435,0.0001024429,0.00003784426,0.0004375044,0.00002034648,0.002201748,0.0001872841,0.000165735,0.00008233107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006308921,"about_ca_system_score_gemma":0.00004171487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009416087,"about_ca_topic_score_gemma":8.59204e-7,"domain_scores_codex":[0.9990271,0.00002622765,0.0001532461,0.0003365089,0.0001941081,0.0002628519],"domain_scores_gemma":[0.9993603,0.00007535666,0.00006330874,0.0003370809,0.00009193901,0.00007203318],"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":[0.00000618783,0.00002759748,0.001323003,0.00000662491,0.000007570095,0.000006116404,0.00008978036,0.7271755,0.0009786076,0.0009214585,0.0002696596,0.2691878],"study_design_scores_gemma":[0.0002109618,0.00001586186,0.001972609,0.00003022297,0.000002931307,0.00001280778,0.000002795299,0.9911428,0.004635382,0.001749854,0.00008294026,0.0001408028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02990422,0.00003135071,0.9674104,0.0001043417,0.001032362,0.0001374204,2.496604e-7,0.0001291488,0.001250438],"genre_scores_gemma":[0.7231538,0.000002697388,0.2762878,0.0004121005,0.00008017818,0.000002571205,8.106678e-7,0.000008565775,0.00005143441],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6932496,"threshold_uncertainty_score":0.4177499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02247821131151898,"score_gpt":0.3302450936995344,"score_spread":0.3077668823880154,"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."}}