{"id":"W3203192700","doi":"10.1109/tnnls.2021.3116212","title":"SmithNet: Strictness on Motion-Texture Coherence for Anomaly Detection","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Anomaly detection; Coherence (philosophical gambling strategy); Artificial intelligence; Convolutional neural network; Encoder; Benchmark (surveying); Computer vision; Pattern recognition (psychology); Frame (networking); Encoding (memory); Motion (physics); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001128392,0.001494743,0.0009462977,0.001243071,0.0004455415,0.0008342754,0.001895586,0.001102019,0.002952346],"category_scores_gemma":[0.003208711,0.0004820854,0.0006446695,0.0009704502,0.0009282641,0.002525983,0.001826591,0.001286773,0.0007982711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009852435,"about_ca_system_score_gemma":0.001603692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009394706,"about_ca_topic_score_gemma":0.01408182,"domain_scores_codex":[0.9993806,0.00008056005,0.00004600449,0.0002285594,0.0001631342,0.000101214],"domain_scores_gemma":[0.9991399,0.00023849,0.0001339312,0.0001935599,0.0002102643,0.00008390003],"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":[0.0008258164,0.0003271209,0.01357229,0.0003039321,0.0002612149,0.0003375168,0.0001386104,0.2422118,0.04497994,0.01519468,0.01876277,0.6630843],"study_design_scores_gemma":[0.00002219596,0.0001238552,0.001749438,0.00001358317,0.00002679218,0.000110551,0.00001947842,0.9803242,0.008562329,0.006458355,0.002573652,0.00001546419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1538486,0.001474062,0.8243844,0.0008235101,0.0002959351,0.0002211121,0.001677812,0.01099448,0.006280018],"genre_scores_gemma":[0.7682936,0.0006645961,0.217616,0.0005555811,0.000221,0.0001962494,0.004872968,0.0005365269,0.00704344],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009394706,"threshold_uncertainty_score":0.01868004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01330737408517271,"score_gpt":0.2312941138717725,"score_spread":0.2179867397865998,"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."}}