{"id":"W2905288264","doi":"10.1609/aaai.v33i01.33018885","title":"Connecting Language to Images: A Progressive Attention-Guided Network for Simultaneous Image Captioning and Language Grounding","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Science and Technology Planning Project of Guangdong Province; National Key Research and Development Program of China; China Scholarship Council; National Natural Science Foundation of China","keywords":"Closed captioning; Bounding overwatch; Computer science; Benchmark (surveying); Artificial intelligence; Image (mathematics); Process (computing); Machine learning; Natural language processing; Pattern recognition (psychology)","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":[0.0005729635,0.000198951,0.0002299583,0.00009954707,0.0003312401,0.0004605367,0.0009828554,0.00005268254,0.0000249389],"category_scores_gemma":[0.00132314,0.0001669132,0.00008042301,0.0004719018,0.00006848016,0.0003093903,0.0003710881,0.0002377876,0.00006728993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004695094,"about_ca_system_score_gemma":0.00003791595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001607122,"about_ca_topic_score_gemma":0.000008769976,"domain_scores_codex":[0.9983677,0.00001993589,0.0003938561,0.0005764845,0.0002685445,0.0003734254],"domain_scores_gemma":[0.9983289,0.0004341254,0.0003678752,0.0002925555,0.0004646123,0.0001118814],"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":[0.00007693418,0.00008354239,0.001749071,0.0001863292,0.0000296945,0.000002007723,0.01083458,0.003596854,0.3298697,0.5658741,0.00006019247,0.08763698],"study_design_scores_gemma":[0.0001181508,0.0002828626,0.001685446,0.0008858718,0.00003050282,0.00002202401,0.005529212,0.8895777,0.07674012,0.02454995,0.00005255112,0.0005256294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8573007,0.00003727442,0.1375148,0.002425926,0.0001871255,0.00134679,0.000007238001,0.0001511624,0.00102896],"genre_scores_gemma":[0.9338177,0.000002097466,0.06563579,0.0001621553,0.0001000676,0.0001056725,0.000001756367,0.00001928378,0.0001554446],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8859808,"threshold_uncertainty_score":0.6806522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0302889741580122,"score_gpt":0.3297025353385947,"score_spread":0.2994135611805825,"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."}}