{"id":"W2288122362","doi":"10.1109/cvpr.2016.314","title":"Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1318,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia; Microsoft Research","keywords":"Pooling; Computer science; Object detection; Exploit; Pascal (unit); Artificial intelligence; Intuition; Abstraction; Artificial neural network; Context (archaeology); Machine learning; Pattern recognition (psychology); Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001028852,0.00220781,0.001450868,0.001031611,0.0004746291,0.001195904,0.002204408,0.001143755,0.002396665],"category_scores_gemma":[0.001689794,0.0006433995,0.0009253898,0.0006607053,0.0005249585,0.002354832,0.001600878,0.001273173,0.001222392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007603862,"about_ca_system_score_gemma":0.0007242875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007061274,"about_ca_topic_score_gemma":0.01546721,"domain_scores_codex":[0.999521,0.00006959457,0.00001741107,0.0001989696,0.0001076651,0.00008536532],"domain_scores_gemma":[0.9995814,0.0001194095,0.00005740013,0.000103389,0.0000926048,0.00004582111],"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":[0.001129052,0.0003669735,0.004689866,0.0002676884,0.0003609304,0.0005436338,0.000154469,0.128531,0.04606264,0.005586028,0.02186078,0.7904469],"study_design_scores_gemma":[0.0000206507,0.0001325771,0.001084781,0.00001973199,0.00007349677,0.0001373688,0.00002119201,0.9806588,0.01104732,0.00451832,0.00226186,0.00002394692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1138496,0.003442612,0.8586315,0.0005580827,0.0003891504,0.0001799822,0.001066278,0.01526862,0.006614207],"genre_scores_gemma":[0.6600709,0.0007249878,0.3241304,0.0005834692,0.0002629327,0.0001241058,0.002511054,0.000608441,0.01098379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007061274,"threshold_uncertainty_score":0.01404035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01508798965431453,"score_gpt":0.2423469466133579,"score_spread":0.2272589569590434,"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."}}