{"id":"W4409366285","doi":"10.1609/aaai.v39i9.33026","title":"Personalized Lip Reading: Adapting to Your Unique Lip Movements with Vision and Language","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Subtitles and Audiovisual Media","field":"Arts and Humanities","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Reading (process); Computer science; Communication; Linguistics; Psychology; Artificial intelligence; Philosophy","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":[0.0007165372,0.001535231,0.001033211,0.0006838161,0.0002394194,0.0008815939,0.001384886,0.001092276,0.003544834],"category_scores_gemma":[0.002005844,0.0003288089,0.001022972,0.0003052831,0.0003722793,0.001465202,0.001399606,0.001316137,0.004584169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003280218,"about_ca_system_score_gemma":0.0003566659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00236643,"about_ca_topic_score_gemma":0.003984385,"domain_scores_codex":[0.9994104,0.0001027169,0.000026396,0.0002861351,0.0001188582,0.00005540869],"domain_scores_gemma":[0.9995114,0.0001736194,0.00003097097,0.0001346734,0.0001105972,0.00003883919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006543944,0.0002705282,0.003021384,0.0003900514,0.0002139795,0.0004719018,0.0002558543,0.02565659,0.1471303,0.0008643977,0.01764579,0.8034248],"study_design_scores_gemma":[0.0001239938,0.000638015,0.01144912,0.00009999287,0.0002645458,0.001660142,0.0003902492,0.829118,0.1350878,0.003806212,0.01719576,0.0001661608],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1806368,0.004303318,0.7562303,0.0006364019,0.0007939514,0.0004044102,0.002868449,0.04213527,0.01199099],"genre_scores_gemma":[0.6587014,0.001676227,0.3075128,0.00100241,0.0003387077,0.0003122826,0.009037975,0.001668137,0.01975002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003544834,"threshold_uncertainty_score":0.01185864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07853644866455922,"score_gpt":0.3207978085600127,"score_spread":0.2422613598954535,"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."}}