{"id":"W3120254887","doi":"10.1109/tifs.2021.3053458","title":"Depth as Attention for Face Representation Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Face recognition and analysis","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"RGB color model; Focus (optics); Pattern recognition (psychology); Deep learning; Face (sociological concept); Convolutional neural network; Facial recognition system; Convolution (computer science)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001308187,0.00008721615,0.0001056095,0.0001192314,0.0003347402,0.0002652834,0.00006560131,0.00006200415,0.0000185125],"category_scores_gemma":[0.00002027343,0.00009123099,0.0001127171,0.0003205802,0.0000213084,0.001407522,0.000002414118,0.000133554,0.00004539314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002285419,"about_ca_system_score_gemma":0.00003775782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001693832,"about_ca_topic_score_gemma":0.00003111766,"domain_scores_codex":[0.9992803,0.00003658154,0.0002329149,0.0001484522,0.0001805064,0.0001212784],"domain_scores_gemma":[0.9993528,0.00006595773,0.00009134522,0.0001404443,0.0002823118,0.00006712783],"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":[0.00003841817,0.0001025195,0.00006850266,0.0001058998,0.0001300569,0.000002333232,0.005758974,0.01851215,0.0004765026,0.04533595,0.0004521536,0.9290165],"study_design_scores_gemma":[0.001196775,0.0001467145,0.0002907044,0.00003659817,0.00005904936,0.00004413697,0.002361693,0.9392901,0.03205898,0.0157867,0.008424438,0.0003041099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01984002,0.00001025215,0.9776042,0.0007495941,0.000239397,0.0001247048,0.00001357699,0.00009303246,0.001325275],"genre_scores_gemma":[0.9936997,0.0001300231,0.0054671,0.0003798646,0.00001123385,0.00002706939,0.00006527499,0.000003323428,0.0002163966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9738597,"threshold_uncertainty_score":0.3720292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01585449687978326,"score_gpt":0.2603825994790686,"score_spread":0.2445281025992854,"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."}}