{"id":"W4306882122","doi":"10.48550/arxiv.2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Reinforcement learning; Task (project management); Salient; Imitation; Robot; Representation (politics); Unsupervised learning; Machine learning; Deep learning; Human–computer interaction","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":[0.000786385,0.0007564764,0.0006474599,0.0004240048,0.0002343583,0.0005577214,0.001527771,0.0009485661,0.001482472],"category_scores_gemma":[0.004515306,0.0004627357,0.0005260113,0.0003200822,0.001045467,0.00128988,0.0009352855,0.001173851,0.0003101779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006297118,"about_ca_system_score_gemma":0.0007713568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003705658,"about_ca_topic_score_gemma":0.003886834,"domain_scores_codex":[0.9996145,0.0001106266,0.00001475247,0.000147529,0.00007176856,0.00004082523],"domain_scores_gemma":[0.9988074,0.0006955003,0.0001541331,0.0001984362,0.0000809402,0.00006348937],"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":[0.0002375046,0.0002173848,0.002752653,0.0002200663,0.00008916167,0.0002834529,0.000241749,0.5594494,0.02476858,0.01483283,0.003308125,0.3935991],"study_design_scores_gemma":[0.00001154373,0.00007239731,0.0003724529,0.000008563479,0.000006188824,0.00004445368,0.00001441281,0.9877175,0.004092167,0.007057598,0.0005931415,0.000009609144],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03073862,0.0001942595,0.9659864,0.0001532244,0.00002337816,0.000070501,0.0001024973,0.00155118,0.001180037],"genre_scores_gemma":[0.7644046,0.0002661535,0.2311851,0.0001780609,0.00004544669,0.0002226183,0.0004450912,0.0002174639,0.00303549],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003705658,"threshold_uncertainty_score":0.007368147,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0409648179073554,"score_gpt":0.2176801157903314,"score_spread":0.176715297882976,"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."}}