{"id":"W4312325116","doi":"10.1109/cvpr52688.2022.01606","title":"Learning Program Representations for Food Images and Cooking Recipes","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Compute Canada","funders":"","keywords":"Computer science; Artificial intelligence; Computer graphics (images); Computer vision; Multimedia","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":[0.0004243708,0.0002278734,0.0002712862,0.0002512447,0.0009052258,0.0006777323,0.0003115327,0.00005501715,0.00009331022],"category_scores_gemma":[0.00003204433,0.0002278264,0.00008779186,0.0002698001,0.00005865567,0.0003058243,0.0003346388,0.0005111914,0.00001229329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002301126,"about_ca_system_score_gemma":0.00004316655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001063226,"about_ca_topic_score_gemma":0.000008111642,"domain_scores_codex":[0.9979742,0.0003159496,0.0003288168,0.0007323583,0.0003455168,0.0003031132],"domain_scores_gemma":[0.9988807,0.0003408114,0.000211126,0.0002511978,0.0001794151,0.0001367832],"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":[0.00002145575,0.0001632846,0.0007133669,0.00004017145,0.0000298375,0.0000103459,0.000582731,0.0003378968,0.0002216528,0.0003417761,0.001591035,0.9959465],"study_design_scores_gemma":[0.001581046,0.005630583,0.001971002,0.000184795,0.00003469482,0.0000955428,0.000469015,0.9717451,0.0004308563,0.006234358,0.01104878,0.0005741725],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2620736,0.00009854061,0.7252323,0.009039834,0.001088956,0.0009661983,0.0001532448,0.0006451072,0.0007022214],"genre_scores_gemma":[0.9810494,0.0001481224,0.01672609,0.00103983,0.0002167003,0.0002029226,0.0001730846,0.00002436677,0.0004195156],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9953723,"threshold_uncertainty_score":0.9290491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04658781759865796,"score_gpt":0.3236402620936274,"score_spread":0.2770524444949695,"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."}}