{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01021792,0.001596868,0.0007295343,0.00386236,0.0008061666,0.002509996,0.001543898,0.001844632,0.001246493],"category_scores_gemma":[0.04886937,0.0006922761,0.001169648,0.003716774,0.001827118,0.004192496,0.002614047,0.001657601,0.00112094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001034566,"about_ca_system_score_gemma":0.0008147431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009329983,"about_ca_topic_score_gemma":0.01178386,"domain_scores_codex":[0.9904282,0.004205012,0.0003819101,0.002097271,0.002598239,0.000289325],"domain_scores_gemma":[0.9631105,0.02404051,0.002933864,0.005401398,0.003885025,0.0006286437],"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":[0.001011674,0.0005146722,0.2110453,0.003402836,0.001279763,0.0008237617,0.004953981,0.04825907,0.00961444,0.01031103,0.02650676,0.6822768],"study_design_scores_gemma":[0.00007018865,0.0007059348,0.4910437,0.002441693,0.0006847148,0.009688417,0.008650552,0.3554204,0.01629036,0.03770242,0.07678219,0.0005195085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6563393,0.0570647,0.2595442,0.002035029,0.0004522663,0.0005292129,0.007669341,0.001272421,0.01509358],"genre_scores_gemma":[0.8748779,0.01345791,0.09537064,0.0003495647,0.0002909612,0.0002033512,0.01215039,0.0005872204,0.002711962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01021792,"threshold_uncertainty_score":0.05403817,"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."}}