{"id":"W4297821055","doi":"10.48550/arxiv.2209.05612","title":"Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of Approaches and Challenges","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Western Canada Research Grid; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Object (grammar); Task (project management); Artificial intelligence; Computer vision; Benchmark (surveying); Pose; RGB color model; Ground truth; Key (lock); Cuboid; Augmented reality; Point (geometry); Human–computer interaction; Computer graphics (images); Geography; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000168882,0.0002023722,0.0004018847,0.0007728024,0.0002204421,0.00008243966,0.0005654182,0.0001283845,0.0003423977],"category_scores_gemma":[0.00001222637,0.0002359846,0.0002248715,0.0007432995,0.00006758103,0.000471592,0.0009191575,0.0004438125,0.000006967387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009565248,"about_ca_system_score_gemma":0.00004630525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003179063,"about_ca_topic_score_gemma":0.0005779681,"domain_scores_codex":[0.9982538,0.0003126448,0.0002312644,0.0009442783,0.00009889913,0.000159141],"domain_scores_gemma":[0.9986329,0.0001269876,0.0002811072,0.0007643283,0.00008066687,0.0001139859],"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":[0.0002258077,0.004651497,0.05432424,0.0004221256,0.01865521,0.0007653215,0.02631298,0.78145,0.001335473,0.07490116,0.0002714826,0.03668474],"study_design_scores_gemma":[0.0003267878,0.0001106675,0.06308994,0.00003553728,0.001577171,0.000001981297,0.001254724,0.920364,0.0001971343,0.01215972,0.0004382754,0.0004440682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9437973,0.0001299327,0.05438005,0.000111336,0.0001466941,0.0001298698,0.00004710622,0.0001425265,0.001115187],"genre_scores_gemma":[0.9987637,0.0002581353,0.0005896377,0.00003172664,0.00003446308,0.000002207452,0.0001882435,0.000008768671,0.0001231585],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.138914,"threshold_uncertainty_score":0.9623174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2889049076128805,"score_gpt":0.2565102763264284,"score_spread":0.03239463128645215,"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."}}