{"id":"W4312635677","doi":"10.1109/cvpr52688.2022.00509","title":"Generating Diverse and Natural 3D Human Motions from Text","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":485,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Motion (physics); Computer science; Representation (politics); Set (abstract data type); Artificial intelligence; Snippet; Sampling (signal processing); Computer vision; Space (punctuation); Text generation; Function (biology); Information retrieval; Programming language","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","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002460009,0.0003114294,0.0003003326,0.0003120321,0.001482815,0.0006725581,0.0003629742,0.00007535558,0.001785411],"category_scores_gemma":[0.000005997108,0.0003150263,0.00008858837,0.0002289924,0.0000824778,0.0006643599,0.0005150898,0.0005976959,0.000158163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005070933,"about_ca_system_score_gemma":0.00003159343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001292798,"about_ca_topic_score_gemma":0.00005360017,"domain_scores_codex":[0.9975522,0.0003825079,0.0004012446,0.000877152,0.0004777185,0.000309192],"domain_scores_gemma":[0.9990085,0.0001152342,0.0002182481,0.0003313672,0.0001420786,0.0001845389],"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":[0.00001202773,0.0001992654,0.0002629247,0.00001595482,0.00003827343,0.00005291974,0.001002657,0.0000537761,0.005123207,0.0002215806,0.003750556,0.9892669],"study_design_scores_gemma":[0.00316199,0.001597918,0.01445009,0.0002771391,0.00006330355,0.0001837124,0.0005326985,0.9666511,0.001405063,0.006283575,0.004009026,0.001384342],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8383657,0.00006137296,0.1578802,0.0007515218,0.001752943,0.0003142041,0.0001984297,0.0002431602,0.0004325336],"genre_scores_gemma":[0.9906155,0.0000991587,0.004294955,0.0038513,0.0003996562,0.00006733802,0.0004399184,0.00002003867,0.0002121109],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9878825,"threshold_uncertainty_score":0.9999302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04597789898601981,"score_gpt":0.2749500740160118,"score_spread":0.228972175029992,"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."}}