{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005224882,0.0008548435,0.0007392118,0.002910786,0.0003390181,0.0006178545,0.0007874097,0.0004031836,0.001329943],"category_scores_gemma":[0.001313526,0.0002163307,0.0006384015,0.001457545,0.0003290074,0.001411228,0.0009037554,0.0005741139,0.0006277265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000620936,"about_ca_system_score_gemma":0.0005258016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00332912,"about_ca_topic_score_gemma":0.005718332,"domain_scores_codex":[0.9996455,0.00004034358,0.00002101648,0.0001230903,0.0001279711,0.00004213947],"domain_scores_gemma":[0.9996086,0.00007317135,0.00005596567,0.00009629151,0.0001318616,0.00003411069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000309707,0.0002278767,0.00326686,0.0001478985,0.00009067266,0.0001262918,0.0001299691,0.02564841,0.07243001,0.006379184,0.006285593,0.8849576],"study_design_scores_gemma":[0.00001759962,0.0001831147,0.005962562,0.00002159754,0.0000566747,0.0002007303,0.0001019646,0.9157426,0.04940072,0.02149868,0.006784038,0.00002973151],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07323517,0.0009216631,0.9170126,0.0001496557,0.0000924484,0.0001311302,0.0006518083,0.005538149,0.002267422],"genre_scores_gemma":[0.5649636,0.0004095616,0.4290155,0.0001350134,0.0001293885,0.00009220389,0.002377881,0.0002458501,0.002631025],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00332912,"threshold_uncertainty_score":0.006619513,"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."}}