{"id":"W2749285435","doi":"10.1109/iccv.2017.333","title":"A Spatiotemporal Oriented Energy Network for Dynamic Texture Recognition","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Pooling; Computer science; Representation (politics); Artificial intelligence; Key (lock); Heuristic; Texture (cosmology); Feature (linguistics); Spacetime; Layer (electronics); Pattern recognition (psychology); Convolutional neural network; Image (mathematics); Machine learning","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":[0.0003075182,0.0002483338,0.0002739314,0.00008617519,0.0002663453,0.0004311845,0.001249238,0.0004043108,0.00002031206],"category_scores_gemma":[0.00007478723,0.0002196512,0.00019727,0.000101369,0.00005003173,0.0002564098,0.0006932479,0.000258522,0.00001318155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009074374,"about_ca_system_score_gemma":0.0002095237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001231713,"about_ca_topic_score_gemma":0.00006138728,"domain_scores_codex":[0.9984526,0.00005191983,0.0003149315,0.0006840671,0.0002177408,0.0002787097],"domain_scores_gemma":[0.9977196,0.00005445359,0.0004931691,0.001231681,0.0004265366,0.00007452148],"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":[0.00002258864,0.0000624615,0.00003169465,0.0000963167,0.0000436776,0.000003170628,0.00004398408,0.000007720815,0.0000811315,0.04999991,0.01797595,0.9316314],"study_design_scores_gemma":[0.0002945361,0.000115292,0.0004495127,0.0002576996,0.0000291556,0.000006969739,0.000003742632,0.4560622,0.005220809,0.4339165,0.1029575,0.0006859796],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002292718,0.0001988502,0.9918489,0.001951553,0.001015723,0.0004488655,0.00004239061,0.0007293028,0.00374148],"genre_scores_gemma":[0.1595434,0.0004719129,0.8217073,0.0008149223,0.0006989353,0.0008090863,0.00161712,0.00004887454,0.01428842],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9309454,"threshold_uncertainty_score":0.8957117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03150820304167906,"score_gpt":0.2910504787427994,"score_spread":0.2595422757011204,"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."}}