{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003272718,0.0006437239,0.0007399677,0.0005048655,0.0002039144,0.0005071261,0.0008959553,0.0007074805,0.001496823],"category_scores_gemma":[0.0008032266,0.0003535272,0.0005841035,0.0008797425,0.0003360682,0.0007979053,0.0009100044,0.001099561,0.0006955761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005860435,"about_ca_system_score_gemma":0.000667644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009553631,"about_ca_topic_score_gemma":0.01444098,"domain_scores_codex":[0.9998023,0.00003189415,0.00000823378,0.00007089361,0.00003745577,0.00004925952],"domain_scores_gemma":[0.9997782,0.00005315587,0.0000327917,0.00005335242,0.00005377123,0.00002881805],"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":[0.0002054152,0.0002418795,0.003579791,0.00006984874,0.0001065834,0.0000673868,0.0000591238,0.1304023,0.04098168,0.005906694,0.005452221,0.8129269],"study_design_scores_gemma":[0.00000365251,0.00003699318,0.001702398,0.000005666265,0.00001008138,0.00003401085,0.00001103144,0.9874603,0.005400514,0.004607142,0.0007219501,0.000006395553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04724309,0.0005870785,0.9493858,0.0002277471,0.00007894499,0.00002281909,0.0003289152,0.00119158,0.0009339526],"genre_scores_gemma":[0.8284466,0.0006489754,0.162323,0.0002086078,0.00008051332,0.0000546125,0.0009934775,0.0001360953,0.007108068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009553631,"threshold_uncertainty_score":0.01899606,"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."}}