{"id":"W4312007190","doi":"10.1109/tencon55691.2022.9977467","title":"Attention-Based Accurate and Robust Facial Landmark Detector","year":2022,"lang":"en","type":"article","venue":"TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON)","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Landmark; Computer science; Artificial intelligence; Face (sociological concept); Pattern recognition (psychology); Convolutional neural network; Detector; Feature (linguistics); Pooling; Block (permutation group theory); Weighting; Channel (broadcasting); Computer vision; Feature vector; Position (finance); Algorithm; Embedding; Focus (optics); 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006769562,0.0004368556,0.0005552743,0.0005740508,0.001029223,0.0004244478,0.001260067,0.0001222787,0.004674934],"category_scores_gemma":[0.0001025521,0.0004377502,0.0003067158,0.001377184,0.000201318,0.000671843,0.00045651,0.0006537038,0.0002290742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000181965,"about_ca_system_score_gemma":0.0004959663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001867177,"about_ca_topic_score_gemma":0.0001675132,"domain_scores_codex":[0.9961093,0.0005603415,0.000598954,0.001179792,0.0008929779,0.0006586207],"domain_scores_gemma":[0.9979047,0.0002363785,0.0004193665,0.000810513,0.0002868512,0.0003422124],"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":[0.001008165,0.002478795,0.02747529,0.0006790496,0.00140676,0.002695774,0.004724962,0.02446059,0.0659437,0.01799499,0.1301595,0.7209724],"study_design_scores_gemma":[0.00376809,0.0009221191,0.003165144,0.0001012517,0.0001950617,0.0002484315,0.002510753,0.9365768,0.001912419,0.00242632,0.04614468,0.00202893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3703176,0.0009450598,0.5933727,0.0181764,0.004638354,0.001941609,0.0003602121,0.001843987,0.008404057],"genre_scores_gemma":[0.9889974,0.00020403,0.001365528,0.001298697,0.0001315517,0.0003457925,0.0001018225,0.00003530585,0.007519903],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9121162,"threshold_uncertainty_score":0.9998074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04175368791083664,"score_gpt":0.2408037305096079,"score_spread":0.1990500425987713,"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."}}