{"id":"W4221149779","doi":"10.1109/icra46639.2022.9812195","title":"Generalizable task representation learning from human demonstration videos: a geometric approach","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Robotics and Automation (ICRA)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Robot; Artificial intelligence; Task (project management); Generalization; Representation (politics); Visual servoing; Computer vision; Task analysis; Categorical variable; Machine learning; Mathematics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016181,0.001515848,0.00136896,0.0005505534,0.0002726707,0.0006303194,0.002358368,0.002100387,0.001998234],"category_scores_gemma":[0.007523366,0.0007753471,0.001031892,0.0006734299,0.00153263,0.002212844,0.001947182,0.002290366,0.000359921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001064296,"about_ca_system_score_gemma":0.0009718674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004848529,"about_ca_topic_score_gemma":0.00375858,"domain_scores_codex":[0.9989754,0.0003111292,0.00004835107,0.0004234236,0.0001389899,0.0001027643],"domain_scores_gemma":[0.9967212,0.00186385,0.0003843294,0.0006583525,0.0002446458,0.0001275404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002236631,0.0001576143,0.0007566598,0.0002417943,0.00007109913,0.0001765301,0.0001849854,0.8081244,0.01266363,0.007122737,0.001773093,0.1685038],"study_design_scores_gemma":[0.00002537635,0.0001502711,0.0003344547,0.000009732486,0.000007740133,0.0000476961,0.00002608446,0.9875195,0.002421256,0.008966864,0.0004791185,0.00001186613],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02170802,0.0001767709,0.9765645,0.0002051321,0.00001285068,0.00007622533,0.0001028609,0.0006813595,0.0004722741],"genre_scores_gemma":[0.7050991,0.0003862894,0.2892034,0.0003521753,0.00007994399,0.0004820536,0.001032852,0.0002601699,0.003103937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004848529,"threshold_uncertainty_score":0.009640634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05002559006014977,"score_gpt":0.3035205868719538,"score_spread":0.253494996811804,"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."}}