{"id":"W2342726332","doi":"10.1109/tpami.2016.2526008","title":"Dynamic Scene Recognition with Complementary Spatiotemporal Features","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Austrian Science Fund","keywords":"Pooling; Computer science; Artificial intelligence; Feature extraction; Pattern recognition (psychology); Pyramid (geometry); Complementarity (molecular biology); Computer vision; Feature (linguistics); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003111544,0.0007947001,0.0009717215,0.001679485,0.0002661595,0.0009405705,0.001005883,0.0004724413,0.001649914],"category_scores_gemma":[0.001045516,0.0003309197,0.0008562012,0.001539751,0.0003170678,0.001755944,0.001262965,0.0007512537,0.000828854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000487498,"about_ca_system_score_gemma":0.0004485875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0043858,"about_ca_topic_score_gemma":0.006630279,"domain_scores_codex":[0.9996326,0.00002726104,0.00001505249,0.0001386574,0.0001170534,0.00006938318],"domain_scores_gemma":[0.9997175,0.00004781697,0.00004221016,0.00008048751,0.00008104408,0.00003091674],"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":[0.0004227533,0.000126711,0.002347424,0.0002055366,0.000170704,0.0003460839,0.0001341537,0.03613581,0.1546097,0.00677309,0.007497777,0.7912303],"study_design_scores_gemma":[0.00001965816,0.0001911102,0.008342359,0.00004298628,0.0001443215,0.0007227171,0.0001475961,0.8884612,0.07569499,0.01230316,0.01385637,0.00007353177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04986703,0.0007171459,0.9416513,0.0001303544,0.00009999896,0.00008473829,0.001174271,0.003036277,0.003238933],"genre_scores_gemma":[0.4547794,0.0009111888,0.5359897,0.0002091757,0.0001448777,0.0001130384,0.004125534,0.000323459,0.003403528],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0043858,"threshold_uncertainty_score":0.008720517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01946906411455808,"score_gpt":0.2836557943116079,"score_spread":0.2641867301970498,"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."}}