{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T12:18:17Z","timestamp":1779106697133,"version":"3.51.4"},"reference-count":33,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.engappai.2026.114848","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T17:42:40Z","timestamp":1777138960000},"page":"114848","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Multi-modal large language model-based image captioning algorithm in information and communication technology: Bridging the gap between general and industry domain"],"prefix":"10.1016","volume":"177","author":[{"given":"Lianying","family":"Chao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xubin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linfeng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sijie","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"DingCheng","family":"Shan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114848_bib1","series-title":"Phi-3 Technical Report: a Highly Capable Language Model Locally on your Phone Visual Instruction Tuning","author":"Abdin","year":"2024"},{"key":"10.1016\/j.engappai.2026.114848_bib2","series-title":"GPT-4 Technical Report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.engappai.2026.114848_bib3","series-title":"Advances in Neural Information Processing Systems","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"10.1016\/j.engappai.2026.114848_bib4","series-title":"Gemini: a Family of Highly Capable Multimodal Models","author":"Anil","year":"2023"},{"key":"10.1016\/j.engappai.2026.114848_bib5","series-title":"Qwen2.5-VL Technical Report","author":"Bai","year":"2025"},{"key":"10.1016\/j.engappai.2026.114848_bib6","article-title":"An overview of domain-specific foundation model: key technologies, applications and challenges","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2409.04267"},{"key":"10.1016\/j.engappai.2026.114848_bib7","series-title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","author":"Chen","year":"2024"},{"key":"10.1016\/j.engappai.2026.114848_bib8","author":"Contributors"},{"key":"10.1016\/j.engappai.2026.114848_bib9","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.engappai.2026.114848_bib10","series-title":"From LLM to NMT: Advancing Low-Resource Machine Translation with Claude","author":"Enis","year":"2024"},{"key":"10.1016\/j.engappai.2026.114848_bib11","author":"Grok"},{"key":"10.1016\/j.engappai.2026.114848_bib12","series-title":"Advances in Neural Information Processing Systems (Neurips)","first-page":"11135","article-title":"Image captioning: transforming objects into words","author":"Herdade","year":"2019"},{"key":"10.1016\/j.engappai.2026.114848_bib13","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4634","article-title":"Attention on attention for image captioning","author":"Huang","year":"2019"},{"issue":"12","key":"10.1016\/j.engappai.2026.114848_bib14","doi-asserted-by":"crossref","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","article-title":"Babytalk: understanding and generating simple image descriptions","volume":"35","author":"Kulkarni","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.114848_bib15","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.engappai.2026.114848_bib16","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.engappai.2026.114848_bib17","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26296","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2024"},{"key":"10.1016\/j.engappai.2026.114848_bib18","series-title":"ClipCap: CLIP Prefix for Image Captioning","author":"Mokady","year":"2021"},{"key":"10.1016\/j.engappai.2026.114848_bib19","series-title":"Understanding Multimodal Llms: the Mechanistic Interpretability of Llava in Visual Question Answering","author":"Qi","year":"2024"},{"key":"10.1016\/j.engappai.2026.114848_bib20","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.engappai.2026.114848_bib21","series-title":"Retrieval-Augmented Image Captioning","author":"Ramos","year":"2023"},{"key":"10.1016\/j.engappai.2026.114848_bib22","series-title":"Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning","author":"Seed","year":"2025"},{"key":"10.1016\/j.engappai.2026.114848_bib23","series-title":"Hunyuan-Large: an open-source Moe Model with 52 Billion Activated Parameters by Tencent","author":"Sun","year":"2024"},{"key":"10.1016\/j.engappai.2026.114848_bib24","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3156","article-title":"Show and tell: a neural image caption generator","author":"Vinyals","year":"2015"},{"key":"10.1016\/j.engappai.2026.114848_bib25","article-title":"MinerU: an open-source solution for precise document content extraction","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2409.18839"},{"key":"10.1016\/j.engappai.2026.114848_bib26","article-title":"General OCR theory: towards OCR-2.0 via a unified end-to-end model","author":"Wei","year":"2024","journal-title":"arXiv preprint arXiv:2409.01704"},{"key":"10.1016\/j.engappai.2026.114848_bib27","series-title":"European Conference on Computer Vision (ECCV)","first-page":"408","article-title":"Vary: scaling up the vision vocabulary for large vision-language model","author":"Wei","year":"2024"},{"key":"10.1016\/j.engappai.2026.114848_bib28","series-title":"International Conference on Machine Learning","first-page":"2048","article-title":"Show, attend and tell: neural image caption generation with visual attention","author":"Xu","year":"2015"},{"key":"10.1016\/j.engappai.2026.114848_bib29","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10685","article-title":"Auto-encoding scene graphs for image captioning","author":"Yang","year":"2019"},{"key":"10.1016\/j.engappai.2026.114848_bib30","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"684","article-title":"Exploring visual relationship for image captioning","author":"Yao","year":"2018"},{"key":"10.1016\/j.engappai.2026.114848_bib31","article-title":"ChatGLM: a family of large language models from GLM-130B to GLM-4 all tools","author":"Zeng","year":"2024","journal-title":"arXiv preprint arXiv:2406.12793"},{"key":"10.1016\/j.engappai.2026.114848_bib33","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"13041","article-title":"Unified vision-language pre-training for image captioning and VQA","author":"Zhou","year":"2020"},{"key":"10.1016\/j.engappai.2026.114848_bib34","series-title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","author":"Zhu","year":"2025"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626011309?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626011309?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T11:59:22Z","timestamp":1779105562000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626011309"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":33,"alternative-id":["S0952197626011309"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114848","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-modal large language model-based image captioning algorithm in information and communication technology: Bridging the gap between general and industry domain","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114848","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114848"}}