{"id":"W4200635486","doi":"10.1609/aaai.v36i3.20243","title":"MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-Based Image Captioning","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Key Research and Development Program of China","keywords":"Closed captioning; Computer science; Artificial intelligence; Natural language processing; Inference; MAGIC (telescope); Sentence; Image (mathematics)","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":[0.0006463216,0.0002128278,0.0002087443,0.0002028424,0.000917053,0.0001898079,0.001361439,0.00005670176,0.0001205865],"category_scores_gemma":[0.0007161337,0.000194347,0.000124243,0.0006249025,0.000313915,0.0003848605,0.0006339097,0.0004366042,0.00001595053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008071475,"about_ca_system_score_gemma":0.0001722729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002682291,"about_ca_topic_score_gemma":0.000008731336,"domain_scores_codex":[0.9980696,0.00004197356,0.0004462488,0.0006051481,0.0005367034,0.000300322],"domain_scores_gemma":[0.9982684,0.0004068016,0.0004382277,0.0002744629,0.0005210633,0.00009102539],"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":[0.0001295709,0.0001626841,0.001757133,0.00002684435,0.00001374317,2.318253e-7,0.0009328169,0.005734247,0.02263709,0.9482769,0.00004724774,0.02028154],"study_design_scores_gemma":[0.000167149,0.0002254591,0.002998485,0.00003577556,0.00001984335,0.000003019663,0.0004624599,0.8610538,0.01472203,0.1198699,0.0001729675,0.0002691247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2076304,0.00001098996,0.7765041,0.0105388,0.0005263461,0.001641389,0.00008592793,0.0002585402,0.0028035],"genre_scores_gemma":[0.926774,0.000002103571,0.07271465,0.0001743694,0.00004351519,0.0002036185,0.000005316472,0.00001293205,0.00006953301],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8553195,"threshold_uncertainty_score":0.792524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05780263208315548,"score_gpt":0.305284387201188,"score_spread":0.2474817551180325,"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."}}