{"id":"W2994810768","doi":"10.1109/iccv.2019.00931","title":"Sequence Level Semantics Aggregation for Video Object Detection","year":2019,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":252,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Discriminative model; Semantics (computer science); Artificial intelligence; Frame (networking); Pipeline (software); Object (grammar); Feature (linguistics); Sequence (biology); Object detection; Cluster analysis; Computer vision; Dependency (UML); Pattern recognition (psychology)","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":[0.0002564907,0.0000892954,0.00008802608,0.0001042325,0.0001129849,0.0001228051,0.0002340963,0.00004916022,0.00002500711],"category_scores_gemma":[0.0000440644,0.00008099307,0.00007601143,0.00031042,0.00001082422,0.0006576777,0.00004348092,0.00005867269,0.0002840746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005541588,"about_ca_system_score_gemma":0.00002912692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003370742,"about_ca_topic_score_gemma":0.0000546749,"domain_scores_codex":[0.9991287,0.00002963979,0.000173281,0.0003068939,0.0001898942,0.0001715938],"domain_scores_gemma":[0.9994199,0.00004768179,0.00007896169,0.0002768181,0.0001362559,0.00004041862],"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":[0.00003406362,0.0001059712,0.001543292,0.0001229533,0.00002952455,0.000001815339,0.0004499797,0.0005722271,0.4462697,0.09663557,0.0003783096,0.4538566],"study_design_scores_gemma":[0.0005687919,0.0003850411,0.003123521,0.00002205784,0.000005944004,0.00003292016,0.00005469725,0.7071979,0.2765985,0.007315516,0.004444384,0.0002507498],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1249665,0.000005273483,0.8722968,0.0002318916,0.0009997626,0.0003271862,0.000001325306,0.0002419845,0.0009292857],"genre_scores_gemma":[0.9799349,0.000002525644,0.01704468,0.0003606465,0.00004351151,0.0000251954,0.000002013415,0.000006553681,0.002579925],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8552521,"threshold_uncertainty_score":0.3651299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05828137332646139,"score_gpt":0.3048723749771711,"score_spread":0.2465910016507097,"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."}}