{"id":"W3011279779","doi":"10.1109/iccvw.2019.00458","title":"FaceSyncNet: A Deep Learning-Based Approach for Non-Linear Synchronization of Facial Performance Videos","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Landmark; Artificial intelligence; Synchronization (alternating current); Deep learning; Computer vision; Frame (networking); Similarity (geometry); Face (sociological concept); Speech recognition; Video tracking; Noise (video); Video processing; 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":[0.000177553,0.0001047966,0.0001548432,0.00008065205,0.00008950008,0.00005306716,0.0003975312,0.00005912626,0.00002457931],"category_scores_gemma":[0.00003166902,0.00008977969,0.00004955983,0.0002861218,0.00002187158,0.0004043456,0.00005351425,0.0000783915,0.00003008195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002185484,"about_ca_system_score_gemma":0.00009780064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004459038,"about_ca_topic_score_gemma":9.510452e-7,"domain_scores_codex":[0.9991077,0.00001298294,0.0001834055,0.0002797979,0.0001981772,0.0002179331],"domain_scores_gemma":[0.9994588,0.00003597705,0.0001222547,0.0002070124,0.0001353842,0.00004056862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004819843,0.0001530635,0.0338434,0.0006551697,0.00002058667,3.323017e-7,0.0005792393,0.511001,0.01020236,0.0001311251,0.00007212081,0.4432934],"study_design_scores_gemma":[0.0005023424,0.0001935596,0.0006385666,0.00001760507,0.000002526189,8.662975e-7,0.0000191742,0.8596379,0.1384561,0.00001095416,0.0004106646,0.0001097469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1105647,0.00002448707,0.8875896,0.00004667875,0.00007418534,0.0002848239,5.025024e-7,0.0000811781,0.001333774],"genre_scores_gemma":[0.7701369,0.000002192448,0.2293915,0.00009539739,0.00002634496,0.00001384497,0.000009596564,0.000007314662,0.0003169315],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6595721,"threshold_uncertainty_score":0.366111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009690627725708554,"score_gpt":0.227373209199405,"score_spread":0.2176825814736965,"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."}}