{"id":"W2765511077","doi":"10.1109/icassp.2018.8462653","title":"High Efficiency Compression for Object Detection","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Video Coding and Compression Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Object detection; Artificial intelligence; Computer vision; Object (grammar); Image compression; Compression (physics); Data compression; Bit rate; Analytics; Real-time computing; Image (mathematics); Pattern recognition (psychology); Image processing; Data mining","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":[0.0003185196,0.0003098811,0.0003492792,0.0002874484,0.000344971,0.0003502637,0.002622163,0.0004798115,0.00001566267],"category_scores_gemma":[0.0001508471,0.0002409071,0.0001951276,0.0002251441,0.00008520442,0.0001394289,0.003611831,0.0004175616,0.00004718172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006675177,"about_ca_system_score_gemma":0.00008608973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007036064,"about_ca_topic_score_gemma":0.000007496164,"domain_scores_codex":[0.9979284,0.00005668626,0.0003516469,0.000976101,0.000319709,0.0003674455],"domain_scores_gemma":[0.9976766,0.0001623417,0.0002599981,0.001602976,0.0002371628,0.00006093525],"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":[0.00006188737,0.0003155995,0.00004488034,0.0004150606,0.0000781827,0.00000582245,0.0003235511,0.003057275,0.01697255,0.0383585,0.03627338,0.9040933],"study_design_scores_gemma":[0.0004300682,0.000395825,0.0001900312,0.0003384474,0.00001636161,0.000007427525,0.00002151506,0.3104917,0.5195811,0.1626205,0.005279554,0.00062752],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01906995,0.0001761106,0.9718899,0.0005078584,0.003891995,0.0005437205,0.000005821496,0.002992262,0.0009223845],"genre_scores_gemma":[0.8736652,0.0000317788,0.1251411,0.00009655212,0.0001970224,0.0002378622,0.000005589086,0.0000158749,0.0006090277],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9034658,"threshold_uncertainty_score":0.9823906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02900021686062963,"score_gpt":0.2759787806943657,"score_spread":0.2469785638337361,"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."}}