{"id":"W4205260486","doi":"10.1109/tpami.2021.3139918","title":"Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Key Research and Development Program of Zhejiang Province; Ministry of Education, India; National Key Research and Development Program of China; Ministry of Earth Sciences","keywords":"Computer science; Artificial intelligence; Motion (physics); Context (archaeology); Kinematics; Motion capture; Representation (politics); Pose; Computer vision; Task (project management); Focus (optics); Machine learning; Sequence (biology); Engineering","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":[0.0003480463,0.000149152,0.0001831261,0.0005437814,0.0009793171,0.0001565989,0.0001443371,0.00003774327,0.00007952756],"category_scores_gemma":[0.00001166974,0.0001589099,0.0001332712,0.0006224085,0.00003380404,0.00046467,0.000009369315,0.0002330939,0.00000264387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005188119,"about_ca_system_score_gemma":0.00001294544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004356448,"about_ca_topic_score_gemma":0.0002107039,"domain_scores_codex":[0.9985707,0.0001285357,0.0003773179,0.0005191818,0.0002426019,0.0001616902],"domain_scores_gemma":[0.9993078,0.0001304446,0.0001259804,0.0002411171,0.00009936428,0.00009525528],"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":[0.000004858341,0.00009678156,0.0003054191,0.00001390792,0.000147137,7.827936e-7,0.0006759212,0.2713301,0.0004426807,0.000129329,0.000005059284,0.726848],"study_design_scores_gemma":[0.0001536409,0.0001237375,0.0003444444,0.000009570923,0.0002551711,0.00001386816,0.0001885221,0.9900767,0.006960264,0.001711191,0.00002130118,0.0001416542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02524735,0.00004989259,0.9735007,0.000371483,0.0002836487,0.0002727105,0.0001380713,0.000108733,0.00002745481],"genre_scores_gemma":[0.995187,0.00008744136,0.004044048,0.000325312,0.00003009372,0.0001785078,0.00005654601,0.00001000018,0.00008103175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9699396,"threshold_uncertainty_score":0.7532215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0377951618617292,"score_gpt":0.28639939249695,"score_spread":0.2486042306352207,"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."}}