{"id":"W3037533539","doi":"10.1609/aaai.v34i07.6833","title":"Learning Cross-Modal Context Graph for Visual Grounding","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Ground; Artificial intelligence; Phrase; Graph; Modal; Modular design; Natural language processing; Theoretical computer science; Programming language","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":[0.0005870227,0.001831929,0.001240217,0.002606648,0.0008389349,0.00102379,0.002966189,0.00242891,0.005064636],"category_scores_gemma":[0.002567922,0.0005973206,0.001427728,0.002427454,0.001109573,0.00332941,0.002529755,0.002049158,0.00200907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00109643,"about_ca_system_score_gemma":0.001001414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01086318,"about_ca_topic_score_gemma":0.02273102,"domain_scores_codex":[0.9992458,0.000105887,0.00002144416,0.0004066438,0.0001176081,0.0001027192],"domain_scores_gemma":[0.9994197,0.00017625,0.00007251839,0.0001638936,0.0001160098,0.00005162849],"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":[0.0003843335,0.0003597562,0.003393093,0.0004006697,0.0002145729,0.0004194688,0.0003613058,0.1947403,0.03766751,0.02394221,0.02364708,0.7144697],"study_design_scores_gemma":[0.0000361664,0.00008797261,0.0008813867,0.00003313951,0.00004172217,0.000117106,0.000113807,0.9520059,0.006008636,0.03704016,0.003609175,0.00002484054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05740946,0.0009757699,0.9243962,0.0003590833,0.0001207338,0.00015055,0.001277411,0.0109264,0.004384431],"genre_scores_gemma":[0.6647895,0.0004421959,0.3193323,0.0006430533,0.0001077492,0.0002056992,0.007159831,0.001036424,0.00628322],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01086318,"threshold_uncertainty_score":0.02159989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08715630185034338,"score_gpt":0.3538858751306011,"score_spread":0.2667295732802577,"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."}}