{"id":"W2751125921","doi":"10.1016/j.neucom.2017.08.063","title":"Deep appearance and motion learning for egocentric activity recognition","year":2017,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Autoencoder; Deep learning; Generality; Convolutional neural network; Benchmark (surveying); Feature learning; Feature (linguistics); Motion (physics); Representation (politics); Pattern recognition (psychology); Computer vision","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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002041926,0.00009079734,0.00009545869,0.00006769678,0.001307901,0.0004956855,0.0002145649,0.0000404161,0.00000176081],"category_scores_gemma":[0.0001561356,0.00009982292,0.0000404061,0.00004955277,0.00002162633,0.0007709039,0.0001252593,0.0001556842,0.00001942176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001442786,"about_ca_system_score_gemma":0.000006962621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006844651,"about_ca_topic_score_gemma":0.00000235969,"domain_scores_codex":[0.9992139,0.00005122645,0.0001062896,0.0003365774,0.00009671377,0.0001952433],"domain_scores_gemma":[0.9993995,0.00006951812,0.0002215433,0.0001884736,0.00007099834,0.00004996304],"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":[0.000005016241,0.00001831433,0.0006653816,0.00002832352,0.000002794357,0.000002137184,0.00008468165,0.0001748225,0.001351491,0.0001226038,0.000008619355,0.9975358],"study_design_scores_gemma":[0.0005918094,0.00007983543,0.06099596,0.00005553021,0.000007014921,0.00002947317,0.000006613862,0.929611,0.005475635,0.002237858,0.0007402305,0.0001690883],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3797806,0.00001425731,0.6190773,0.000222907,0.0002144239,0.0001479682,1.719518e-7,0.0001131213,0.0004292896],"genre_scores_gemma":[0.9943348,0.00001589231,0.005292403,0.00009723785,0.0002098391,0.00001002384,0.000001615651,0.00000824324,0.00002997723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9973667,"threshold_uncertainty_score":0.9999923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03519900809282327,"score_gpt":0.2690785800960834,"score_spread":0.2338795720032601,"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."}}