{"id":"W2553594924","doi":"10.48550/arxiv.1611.02155","title":"Spatiotemporal Residual Networks for Video Action Recognition","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":494,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Residual; Action recognition; Action (physics); Computer science; Artificial intelligence; Algorithm","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":[0.0005132082,0.001060415,0.0004245536,0.000628106,0.0001599708,0.0005436774,0.001144832,0.0006338031,0.004202052],"category_scores_gemma":[0.00168481,0.0002588624,0.0005368738,0.0007246006,0.0003365891,0.001554796,0.0005947415,0.0009941431,0.001356766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008900215,"about_ca_system_score_gemma":0.0007001007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01129299,"about_ca_topic_score_gemma":0.01667921,"domain_scores_codex":[0.9996812,0.00004806688,0.00001804923,0.0001080803,0.0001033566,0.00004127166],"domain_scores_gemma":[0.9996889,0.00008950389,0.0000437356,0.0000785134,0.000078827,0.00002060546],"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":[0.0003206355,0.0001614299,0.001983745,0.000242275,0.000140176,0.0001460257,0.00004708741,0.3970386,0.02945425,0.01632541,0.0169788,0.5371617],"study_design_scores_gemma":[0.000006662125,0.00005540111,0.0006220989,0.00001216684,0.00001586656,0.00003292289,0.000009860716,0.9814976,0.008207999,0.006448701,0.00308246,0.000008263008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06438205,0.003340008,0.908519,0.0007426158,0.0003064851,0.0001030027,0.002460037,0.01222536,0.007921398],"genre_scores_gemma":[0.7175043,0.002144869,0.2621127,0.0003194148,0.0001638699,0.0001293841,0.006827072,0.0003908592,0.01040762],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01129299,"threshold_uncertainty_score":0.0224545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1533328541270049,"score_gpt":0.2189550402325592,"score_spread":0.06562218610555429,"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."}}