{"id":"W2990128502","doi":"10.1109/iccv.2019.00710","title":"Spatiotemporal Feature Residual Propagation for Action Prediction","year":2019,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Residual; Redundancy (engineering); Kalman filter; Representation (politics); Feature (linguistics); Key (lock); Artificial intelligence; Abstraction; Pattern recognition (psychology); Data mining; Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001378744,0.00006822059,0.00006153798,0.00008644821,0.00009119346,0.0001096605,0.0001081093,0.00007507667,0.00009190961],"category_scores_gemma":[0.00001102512,0.00006039726,0.00003721633,0.0001164019,0.000005366884,0.001052427,0.00001822077,0.00007088755,0.000193845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003816307,"about_ca_system_score_gemma":0.00003407065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007858207,"about_ca_topic_score_gemma":0.00001383002,"domain_scores_codex":[0.9993759,0.00002238613,0.0001068775,0.0002320396,0.0001525092,0.0001102943],"domain_scores_gemma":[0.9995937,0.00002359896,0.00006943715,0.0001722229,0.0001113679,0.00002970253],"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":[0.0001777764,0.0003149771,0.006658534,0.0002807353,0.00007961033,0.000001774645,0.000899136,0.0003568871,0.075379,0.1178758,0.2149779,0.5829978],"study_design_scores_gemma":[0.003513548,0.001510508,0.05890935,0.00009657742,0.00003407374,0.00004470636,0.0002480052,0.3962635,0.3431255,0.02167957,0.1738467,0.0007279458],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1586195,0.000006437035,0.8303956,0.0023045,0.001212896,0.000819833,0.00001060059,0.0004196053,0.00621104],"genre_scores_gemma":[0.9681062,0.000004250735,0.0190833,0.0002925279,0.0003640997,0.0000588267,0.0001563369,0.000008104102,0.01192635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8113123,"threshold_uncertainty_score":0.249155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02694954738140808,"score_gpt":0.2648618365241415,"score_spread":0.2379122891427334,"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."}}