{"id":"W2951329458","doi":"10.48550/arxiv.1406.2031","title":"Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Pascal (unit); Torso; Computer science; Artificial intelligence; Computer vision; Low resolution; Object (grammar); Human body; Representation (politics); Pattern recognition (psychology); High resolution","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004111953,0.0003691545,0.0004267782,0.0002794718,0.0003613026,0.000653938,0.0006869396,0.0002509248,9.368658e-7],"category_scores_gemma":[0.0001816047,0.0004315939,0.00009539477,0.0003657224,0.0001534775,0.001677431,0.002455274,0.000589787,8.481132e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001198315,"about_ca_system_score_gemma":0.00008367807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000288447,"about_ca_topic_score_gemma":0.00003104061,"domain_scores_codex":[0.9976111,0.0001640448,0.0002336458,0.00142487,0.0001072616,0.0004590835],"domain_scores_gemma":[0.99808,0.0002197398,0.0003415485,0.001000364,0.0001553664,0.0002029654],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002060005,0.0001540389,0.006901432,0.002326528,0.0005413983,0.003902926,0.004931058,0.7416322,0.007327457,0.05122659,0.00004346805,0.1808069],"study_design_scores_gemma":[0.0002064863,0.00004269567,0.00008348191,0.0004120505,0.00006612651,0.00004559436,0.000121859,0.8336887,0.008858253,0.1559778,0.00002049027,0.0004765246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3032081,0.0004861111,0.6955348,0.00001337406,0.0001658021,0.0002146251,0.000001652819,0.0002604471,0.0001150905],"genre_scores_gemma":[0.980985,0.001507072,0.01725726,0.00006571899,0.00007479364,8.7437e-7,0.00000159643,0.00002692716,0.00008071263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6782776,"threshold_uncertainty_score":0.9998136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1313291188635368,"score_gpt":0.2465769638115365,"score_spread":0.1152478449479997,"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."}}