{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006859877,0.00139621,0.0007764713,0.001221506,0.0003741527,0.0007770343,0.001850739,0.0009141959,0.002788065],"category_scores_gemma":[0.001639491,0.0005256883,0.0007026075,0.000794741,0.0003929325,0.002185488,0.00106574,0.001072667,0.001009923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008490426,"about_ca_system_score_gemma":0.001425844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01387973,"about_ca_topic_score_gemma":0.01222236,"domain_scores_codex":[0.999741,0.00003169735,0.00001309265,0.00009449842,0.00007928726,0.00004045702],"domain_scores_gemma":[0.9997306,0.00006566223,0.00004052047,0.0000537357,0.00008935778,0.00002000231],"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":[0.0003477251,0.0001982774,0.001580359,0.0001549833,0.0001705275,0.0001005125,0.00004996479,0.3311662,0.01551527,0.007407332,0.01672766,0.6265813],"study_design_scores_gemma":[0.000007456203,0.00001120941,0.00009624675,0.000003394956,0.000005104648,0.00001465345,0.000001896317,0.9955307,0.002328232,0.001199966,0.0007958933,0.000005273668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009613269,0.0004176451,0.98163,0.0001229854,0.00009052637,0.00006809076,0.0003797675,0.006756137,0.0009216996],"genre_scores_gemma":[0.3440225,0.0008659251,0.6431467,0.000239198,0.000153708,0.0002545828,0.003469536,0.0006810775,0.007166835],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01387973,"threshold_uncertainty_score":0.0275979,"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."}}