{"id":"W3207758636","doi":"10.1007/s11263-021-01531-2","title":"Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100","year":2021,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":364,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; University of Toronto; Ministero dell’Istruzione, dell’Università e della Ricerca","keywords":"Computer science; Pipeline (software); Artificial intelligence; Action (physics); Task (project management); Anticipation (artificial intelligence); Adaptation (eye); EPIC; Action recognition; Pattern recognition (psychology); Computer vision; Psychology","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":[0.001606305,0.003073334,0.001651027,0.003081725,0.001098175,0.001759382,0.003116095,0.001538242,0.008242854],"category_scores_gemma":[0.004259138,0.0007490141,0.001786663,0.003035204,0.001018718,0.001916182,0.004126439,0.002323846,0.01330038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001716428,"about_ca_system_score_gemma":0.002486984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05154839,"about_ca_topic_score_gemma":0.1033388,"domain_scores_codex":[0.9970908,0.0003194739,0.0001241264,0.001272666,0.0007381146,0.0004547899],"domain_scores_gemma":[0.9982224,0.000124651,0.00007066281,0.0008009624,0.0005202119,0.0002610624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009172093,0.0008200296,0.01056053,0.0009635978,0.0003713644,0.0005945651,0.0004566157,0.01449619,0.02445601,0.001921825,0.5471904,0.3972517],"study_design_scores_gemma":[0.0005659673,0.001369082,0.09785337,0.0008329621,0.000312697,0.002736941,0.001738954,0.241991,0.04838576,0.01199367,0.5916935,0.0005260439],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.2147837,0.008412726,0.1423314,0.002084093,0.003779253,0.00311137,0.3684555,0.2156271,0.04141485],"genre_scores_gemma":[0.1160863,0.0008088891,0.1084601,0.0006430381,0.0001825127,0.0008917701,0.7604288,0.003446959,0.009051668],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.05154839,"threshold_uncertainty_score":0.1024967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.031786217904964,"score_gpt":0.3117536532749697,"score_spread":0.2799674353700057,"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."}}