{"id":"W4386171497","doi":"10.1016/j.patcog.2023.109918","title":"InvFlow: Involution and multi-scale interaction for unsupervised learning of optical flow","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Optical flow; Convolution (computer science); Artificial intelligence; Encoder; Convolutional neural network; Artificial neural network; Pattern recognition (psychology); Feature (linguistics); Computer vision; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000189102,0.00007289954,0.00009750873,0.000142067,0.00008383013,0.00004014557,0.00007940028,0.00003523799,0.000007069253],"category_scores_gemma":[0.0001055016,0.00007454333,0.00003767035,0.0001921915,0.00002129622,0.0005232751,0.00007705302,0.00009613999,0.00004483432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001813917,"about_ca_system_score_gemma":0.000007051105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007968858,"about_ca_topic_score_gemma":0.000006495169,"domain_scores_codex":[0.9993252,0.00003887459,0.0001734223,0.0002250231,0.00009579657,0.0001417332],"domain_scores_gemma":[0.9995835,0.0001213733,0.00006428931,0.00008717688,0.00009894544,0.00004465562],"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":[0.000007379763,0.00002198011,0.001348766,0.00004184856,0.000003438515,5.824897e-7,0.0003904403,0.0001107852,0.01082929,0.000004690177,0.00003433255,0.9872065],"study_design_scores_gemma":[0.0005879542,0.00007521341,0.008231315,0.00009881594,0.000005001928,0.000004935129,0.0001828929,0.976425,0.01359071,0.0005487577,0.0001539549,0.00009548048],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1492908,0.00001358134,0.8499711,0.0002149263,0.0002045481,0.000134422,0.000004658782,0.0001322765,0.00003362832],"genre_scores_gemma":[0.8291849,0.00006293655,0.1703911,0.0001352029,0.0000503364,0.00003886225,0.00009054223,0.00001096308,0.0000351177],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.987111,"threshold_uncertainty_score":0.3039789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06289675201136713,"score_gpt":0.3144779288684079,"score_spread":0.2515811768570407,"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."}}