{"id":"W2971143541","doi":"10.1016/j.neucom.2019.08.040","title":"Optical flow estimation using channel attention mechanism and dilated convolutional neural networks","year":2019,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"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; Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Feature (linguistics); Optical flow; Channel (broadcasting); Convolution (computer science); Upsampling; Encoder; Artificial neural network; Feature extraction; Image (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":[0.0006893822,0.0006689053,0.0007218128,0.0008775255,0.000492089,0.0006205438,0.0009220791,0.0009109561,0.001719628],"category_scores_gemma":[0.001663542,0.0004363402,0.0005960921,0.0007180849,0.0004132972,0.001390784,0.0008476768,0.0009991851,0.0003408401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006859612,"about_ca_system_score_gemma":0.001201811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0100818,"about_ca_topic_score_gemma":0.01047334,"domain_scores_codex":[0.9997535,0.00003829441,0.00001149633,0.00008809911,0.00005423065,0.00005441327],"domain_scores_gemma":[0.9995025,0.0001461779,0.00005776671,0.00007586581,0.0001827852,0.00003486336],"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":[0.0004435723,0.0002438211,0.002582371,0.0001145364,0.0001511691,0.0001459689,0.00008571776,0.2481935,0.0748959,0.01456544,0.004962362,0.6536157],"study_design_scores_gemma":[0.000006566772,0.00001705454,0.0004179642,0.00000307683,0.00001351886,0.00001772966,0.000003257299,0.9917854,0.005649729,0.001646073,0.0004325875,0.00000714661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02803379,0.000311444,0.9695035,0.0001576653,0.0001015644,0.00003143605,0.0000504343,0.0005960148,0.00121418],"genre_scores_gemma":[0.6645822,0.0004956423,0.3278498,0.0002168905,0.0001869642,0.00006288429,0.0002745246,0.0001203752,0.006210791],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0100818,"threshold_uncertainty_score":0.02004623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01356575033297846,"score_gpt":0.2517082581350247,"score_spread":0.2381425078020462,"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."}}