{"id":"W4383904392","doi":"10.1016/j.jvcir.2023.103890","title":"EMHIFormer: An Enhanced Multi-Hypothesis Interaction Transformer for 3D human pose estimation in video","year":2023,"lang":"en","type":"article","venue":"Journal of Visual Communication and Image Representation","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Transformer; Ambiguity; Monocular; Pose; Artificial intelligence; Exploit; Machine learning; Pattern recognition (psychology)","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":[0.0007585572,0.0000943112,0.0001659998,0.000526541,0.0002099795,0.0002203582,0.0002345487,0.00005299234,0.00001537636],"category_scores_gemma":[0.0001656735,0.00009239501,0.00006934779,0.0003809239,0.00003450527,0.003801157,0.00002547531,0.0001602813,0.0000103281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005545321,"about_ca_system_score_gemma":0.00002643144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002737805,"about_ca_topic_score_gemma":0.00004736444,"domain_scores_codex":[0.9987637,0.0002180353,0.0005681722,0.0001483453,0.0001814354,0.0001203117],"domain_scores_gemma":[0.9987616,0.000257221,0.0004139122,0.0002152194,0.0002921576,0.00005989396],"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":[0.0001263133,0.0005039923,0.0001784184,0.00005438241,0.00003511332,0.000002069419,0.006283741,0.0003911381,0.3046509,0.0004372465,0.0002574372,0.6870793],"study_design_scores_gemma":[0.0040623,0.0009344953,0.04718883,0.0002475754,0.00004736927,0.00005487125,0.00344686,0.7974159,0.1390177,0.006839389,0.0004136871,0.000331111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4497298,0.00002357263,0.5491802,0.0005063539,0.00009802775,0.0002447813,0.000001564734,0.0000435796,0.0001721157],"genre_scores_gemma":[0.9216251,0.0003781327,0.07775266,0.00007264235,0.00003793946,0.00002842868,0.00004779133,0.000009646652,0.0000475961],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7970247,"threshold_uncertainty_score":0.3767759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07978889878690541,"score_gpt":0.4256775931218845,"score_spread":0.345888694334979,"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."}}