{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001102225,0.0001791107,0.0002019792,0.0003813124,0.0001821598,0.00008099036,0.0002561277,0.00002553575,0.000190572],"category_scores_gemma":[0.000001539731,0.0001115555,0.0001041866,0.0005968983,0.00006707173,0.0004163167,0.000005034228,0.0001272343,0.00002996951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003685972,"about_ca_system_score_gemma":0.00001205441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000389979,"about_ca_topic_score_gemma":0.002409034,"domain_scores_codex":[0.998841,0.00005560993,0.0002321397,0.0004625409,0.0002139571,0.0001947295],"domain_scores_gemma":[0.9993229,0.00007271949,0.00008977152,0.0003445441,0.00006736027,0.0001027079],"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":[0.00001346452,0.00007873859,0.000512092,0.00000417281,0.0001480537,0.000006708727,0.00007056659,0.0003783069,0.0005173928,0.000007132926,0.000004475708,0.9982589],"study_design_scores_gemma":[0.00111872,0.0007765862,0.01845662,0.0003153324,0.0007076359,0.00009670277,0.0001527964,0.5495223,0.4259178,0.001480759,0.0002639154,0.001190861],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001443158,0.00005133854,0.9966086,0.001554444,0.00008312768,0.00009388741,0.00005663349,0.00008523177,0.0000235799],"genre_scores_gemma":[0.9543749,0.000276297,0.04450636,0.0006266691,0.000005119026,0.00001064773,0.00000821404,0.000008793291,0.0001829884],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.997068,"threshold_uncertainty_score":0.45491,"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."}}