{"id":"W4394597738","doi":"10.1109/wacv57701.2024.00104","title":"Framework-agnostic Semantically-aware Global Reasoning for Segmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario; Canadian Institute for Advanced Research; Vector Institute; Compute Canada; Government of Canada","keywords":"Computer science; Segmentation; Artificial intelligence; Information retrieval; Natural language processing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001193144,0.001176604,0.0008694076,0.001063101,0.0004315391,0.001458623,0.002654344,0.001210726,0.003886968],"category_scores_gemma":[0.002300079,0.0005258524,0.00170703,0.0008824848,0.001085015,0.003888877,0.002089494,0.002103655,0.001538004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001539647,"about_ca_system_score_gemma":0.001852093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008079009,"about_ca_topic_score_gemma":0.01689913,"domain_scores_codex":[0.999376,0.00008712198,0.00003193423,0.0002453128,0.0001710098,0.00008869267],"domain_scores_gemma":[0.9993824,0.0001595504,0.00005188416,0.0002465074,0.0001102611,0.00004933167],"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":[0.0004400115,0.0003314593,0.002490558,0.0004176538,0.0002376744,0.0003183947,0.000468619,0.2373411,0.07391302,0.0419717,0.01228194,0.6297879],"study_design_scores_gemma":[0.00001922475,0.00005969762,0.0004318217,0.00001981181,0.00005801347,0.00008565615,0.00005907684,0.9362344,0.02034918,0.0390681,0.00359689,0.00001816994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01437341,0.0002637685,0.9716413,0.0001674993,0.00003597236,0.0000859167,0.000429268,0.01127204,0.001730745],"genre_scores_gemma":[0.3896042,0.000339942,0.6026628,0.0003376402,0.00003958613,0.00009917672,0.002816977,0.0008601213,0.003239546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008079009,"threshold_uncertainty_score":0.01606399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02264637164427088,"score_gpt":0.3239686427315151,"score_spread":0.3013222710872442,"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."}}