{"id":"W4411176006","doi":"10.1016/j.nlp.2025.100159","title":"Next-generation image captioning: A survey of methodologies and emerging challenges from transformers to Multimodal Large Language Models","year":2025,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Closed captioning; Computer science; Transformer; Natural language processing; Artificial intelligence; Image (mathematics); Engineering; Electrical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002763933,0.001803949,0.001250228,0.002030037,0.0005468454,0.00331874,0.002919812,0.001579817,0.008154644],"category_scores_gemma":[0.007123054,0.0006499955,0.001210844,0.002133507,0.001172848,0.006005218,0.002399155,0.002933716,0.00443797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001800867,"about_ca_system_score_gemma":0.00122899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004702269,"about_ca_topic_score_gemma":0.004344603,"domain_scores_codex":[0.9988068,0.0004348879,0.00009053437,0.0002664064,0.000328582,0.00007271207],"domain_scores_gemma":[0.9971882,0.001615964,0.0001220299,0.0004456679,0.0005372076,0.00009099177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001446659,0.000134615,0.0004427795,0.001490465,0.00009842421,0.0001933521,0.0003517866,0.05927686,0.006245237,0.05281987,0.03720463,0.8415973],"study_design_scores_gemma":[0.00002808177,0.0001749141,0.0003467185,0.0004683287,0.00007368151,0.0006253534,0.0002756274,0.795644,0.01426108,0.08294562,0.1050604,0.00009622068],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.005441832,0.04114411,0.9293787,0.003081382,0.0005160657,0.0002277424,0.0008695492,0.007503779,0.01183676],"genre_scores_gemma":[0.1780937,0.07177547,0.7191174,0.002858002,0.001546573,0.0005961126,0.006533983,0.002991729,0.01648697],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.008154644,"threshold_uncertainty_score":0.02727997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0630583087593844,"score_gpt":0.3692293337405086,"score_spread":0.3061710249811243,"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."}}