{"id":"W2064063312","doi":"10.1109/crv.2013.55","title":"OpenVL: Abstracting Vision Tasks Using a Segment-Based Language Model","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Abstraction; Field (mathematics); Artificial intelligence; Segmentation; Task (project management); Computer vision; Image segmentation; Image (mathematics); Human–computer interaction","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":[0.000156502,0.0001222632,0.0001147278,0.00007872607,0.0001085221,0.0002744767,0.0004814756,0.00004791587,0.00007477949],"category_scores_gemma":[0.00003556566,0.0001003337,0.00004900972,0.0002002522,0.00001886154,0.001807369,0.0002090801,0.0001226443,0.00007513965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000477756,"about_ca_system_score_gemma":0.00004105868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002249491,"about_ca_topic_score_gemma":0.000001973846,"domain_scores_codex":[0.9990407,0.00001971753,0.0001858601,0.0002965549,0.0002040157,0.0002531243],"domain_scores_gemma":[0.9992756,0.00005202305,0.00008019102,0.0004387925,0.00007345167,0.0000799635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003375062,0.00008013006,0.0000455569,0.00001744048,0.000005233941,0.00001839024,0.0002318162,0.005416071,0.642868,0.001212288,0.0009213822,0.3491803],"study_design_scores_gemma":[0.0001031296,0.00002696359,0.00003091344,0.00002069514,0.000001408189,0.000003284821,0.00004185377,0.7422726,0.2564971,0.0008333969,0.00005221131,0.000116458],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02967159,0.00004255077,0.9658113,0.000203434,0.00002993818,0.0002368104,6.052958e-7,0.0004582886,0.003545555],"genre_scores_gemma":[0.439132,0.000001615361,0.5599865,0.0005961731,0.0000122881,0.000006767763,0.000001020975,0.000007542552,0.0002560983],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7368565,"threshold_uncertainty_score":0.4091488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02734401857519636,"score_gpt":0.3361073344247567,"score_spread":0.3087633158495603,"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."}}