{"id":"W4396747546","doi":"10.1016/j.jvcir.2024.104174","title":"Multi-hop graph transformer network for 3D human pose estimation","year":2024,"lang":"en","type":"article","venue":"Journal of Visual Communication and Image Representation","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Adjacency matrix; Graph; Convolutional neural network; Transformer; Artificial intelligence; Pattern recognition (psychology); Pose; Theoretical computer science; Algorithm","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":[0.0006537221,0.00008865721,0.0001345715,0.0002148109,0.0002781695,0.0004674808,0.0002175918,0.00004654543,0.00001741837],"category_scores_gemma":[0.00005010866,0.00008017223,0.0001078666,0.0002702984,0.00004733322,0.002131743,0.00002618783,0.0001737976,0.000006027253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002700391,"about_ca_system_score_gemma":0.00003252983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009233967,"about_ca_topic_score_gemma":0.000005964484,"domain_scores_codex":[0.9989863,0.0001493997,0.0004535127,0.0001307393,0.0001730697,0.000106972],"domain_scores_gemma":[0.9990348,0.000207703,0.0002169805,0.0001845181,0.0002972108,0.00005874038],"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":[0.00008354468,0.0004715827,0.0001703713,0.0002384285,0.0002075204,0.00000884464,0.004452799,0.0006243528,0.08418436,0.01321448,0.01044929,0.8858944],"study_design_scores_gemma":[0.001888426,0.0006511459,0.005627588,0.0004678054,0.000128911,0.0001924969,0.0004142842,0.9472721,0.01016321,0.02664395,0.006238799,0.0003112679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01984437,0.0009251833,0.9773331,0.001107901,0.0002372537,0.0002171711,0.000002080066,0.00005468487,0.0002782129],"genre_scores_gemma":[0.636263,0.0008651901,0.3623789,0.0001373418,0.00016838,0.00001643687,0.00004577369,0.00001188224,0.0001130373],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9466478,"threshold_uncertainty_score":0.4507928,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04759473798964078,"score_gpt":0.4013701902620755,"score_spread":0.3537754522724347,"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."}}