{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004929177,0.000245819,0.0002882202,0.0000954405,0.0005195398,0.000536513,0.002146723,0.00009639983,0.00004631963],"category_scores_gemma":[0.001437951,0.0002037562,0.0001945738,0.0007608861,0.0002626716,0.0004341514,0.0004278013,0.0005293433,0.000111715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003718014,"about_ca_system_score_gemma":0.00007875161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007948207,"about_ca_topic_score_gemma":0.000003170936,"domain_scores_codex":[0.9979155,0.00002344784,0.000560823,0.0006738601,0.000427754,0.0003986089],"domain_scores_gemma":[0.998218,0.0002557271,0.0004752457,0.0001938287,0.0006972151,0.0001599816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007289013,0.00007099651,0.002376638,0.00005135041,0.00001519859,1.196468e-7,0.002369402,0.0005097835,0.03775868,0.8646373,0.00003611,0.09210156],"study_design_scores_gemma":[0.00009037555,0.0006694672,0.00168868,0.0001055395,0.00001499486,0.000002812546,0.0008073371,0.7202037,0.1855938,0.08999804,0.0004590502,0.0003662363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5575172,0.00001566281,0.4240799,0.01359325,0.0002728197,0.0009360551,0.000005160762,0.000344264,0.003235617],"genre_scores_gemma":[0.9925161,0.000005850614,0.00655402,0.0005792797,0.0001390671,0.0001025759,0.000001096955,0.00002144407,0.00008054553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7746392,"threshold_uncertainty_score":0.8308936,"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."}}