{"id":"W1952506714","doi":"10.1109/cvpr.2015.7299102","title":"segDeepM: Exploiting segmentation and context in deep neural networks for object detection","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Nvidia","keywords":"Computer science; Artificial intelligence; Segmentation; Pascal (unit); Object detection; Convolutional neural network; Inference; Pattern recognition (psychology); Markov random field; Exploit; Object (grammar); Image segmentation; Context (archaeology); Computer vision","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":[0.00108148,0.00190213,0.001184502,0.001525087,0.000467437,0.0009839048,0.002725731,0.001659347,0.003142188],"category_scores_gemma":[0.001902835,0.0008294434,0.0007646861,0.001072115,0.0005262706,0.002551527,0.00203086,0.00160561,0.001202279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008003951,"about_ca_system_score_gemma":0.001147587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006092651,"about_ca_topic_score_gemma":0.01612712,"domain_scores_codex":[0.9995327,0.00007014465,0.00001477243,0.0001892519,0.0001234603,0.00006966246],"domain_scores_gemma":[0.9996035,0.000139699,0.00003895235,0.0001048751,0.00007733313,0.00003568844],"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":[0.0005090087,0.0002646973,0.003101943,0.0002236779,0.0002413968,0.0002197272,0.00008201082,0.1081836,0.0228339,0.006417994,0.01271772,0.8452043],"study_design_scores_gemma":[0.00002707729,0.0001050636,0.0008087732,0.00002473602,0.0000463597,0.000114494,0.00001685949,0.9707728,0.01379772,0.009217473,0.00505006,0.00001859331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05224468,0.003547592,0.9226838,0.0004153306,0.0002758265,0.0001760886,0.001029878,0.01569242,0.003934423],"genre_scores_gemma":[0.3739874,0.001000618,0.6119057,0.0007424319,0.0001778148,0.0001963128,0.002592919,0.0006033574,0.008793526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006092651,"threshold_uncertainty_score":0.01211435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03750173293701438,"score_gpt":0.2831155187903668,"score_spread":0.2456137858533524,"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."}}