{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:56:46Z","timestamp":1781312206200,"version":"3.54.1"},"reference-count":53,"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"}],"funder":[{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan Province","doi-asserted-by":"publisher","award":["242300421402"],"award-info":[{"award-number":["242300421402"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102133"],"award-info":[{"award-number":["62102133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62362041"],"award-info":[{"award-number":["62362041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.eswa.2026.132042","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T08:38:52Z","timestamp":1773909532000},"page":"132042","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["GLM-EER: Global-Local Memory and Emotion Evaluation Refinement For Emotional Video Description"],"prefix":"10.1016","volume":"322","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0162-230X","authenticated-orcid":false,"given":"Chong","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9026-8128","authenticated-orcid":false,"given":"Shengbo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2391-4249","authenticated-orcid":false,"given":"Pengjie","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7467-7108","authenticated-orcid":false,"given":"Hong","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-4871","authenticated-orcid":false,"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132042_bib0001","series-title":"Proceedings of the 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.eswa.2026.132042_bib0002","series-title":"Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.eswa.2026.132042_bib0003","series-title":"Proceedings of the advances in neural information processing systems","first-page":"1877","article-title":"Language models are few-shot learners","volume":"vol. 33","author":"Brown","year":"2020"},{"key":"10.1016\/j.eswa.2026.132042_bib0004","series-title":"Annual meeting of the association for computational linguistics: Human language technologies","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"Chen","year":"2011"},{"key":"10.1016\/j.eswa.2026.132042_bib0005","series-title":"Proceedings of the european conference on computer vision","first-page":"519","article-title":"Factual or emotional: Stylized image captioning with adaptive learning and attention","author":"Chen","year":"2018"},{"key":"10.1016\/j.eswa.2026.132042_bib0006","series-title":"Proceedings of the advances in neural information processing systems","first-page":"1","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2024"},{"key":"10.1016\/j.eswa.2026.132042_bib0007","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"21393","article-title":"Scenic: A jax library for computer vision research and beyond","author":"Dehghani","year":"2022"},{"key":"10.1016\/j.eswa.2026.132042_bib0008","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19358","article-title":"Eva: Exploring the limits of masked visual representation learning at scale","author":"Fang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132042_bib0009","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3137","article-title":"Stylenet: Generating attractive visual captions with styles","author":"Gan","year":"2017"},{"key":"10.1016\/j.eswa.2026.132042_bib0010","series-title":"Proceedings of the 2nd workshop on multimedia for accessible human computer interfaces","first-page":"25\u201432","article-title":"Semantic enhanced encoder-decoder network (SEN) for video captioning","author":"Gui","year":"2019"},{"key":"10.1016\/j.eswa.2026.132042_bib0011","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13504","article-title":"Ma-lmm: Memory-augmented large multimodal model for long-term video understanding","author":"He","year":"2024"},{"key":"10.1016\/j.eswa.2026.132042_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13894","article-title":"Do you remember? Dense video captioning with cross-modal memory retrieval","author":"Kim","year":"2024"},{"key":"10.1016\/j.eswa.2026.132042_bib0013","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1023\/A:1020346032608","article-title":"Natural language description of human activities from video images based on concept hierarchy of actions","volume":"50","author":"Kojima","year":"2002","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.132042_bib0014","series-title":"Proceedings of the 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.eswa.2026.132042_bib0015","series-title":"Proceedings of the annual meeting of the association for computational linguistics","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.eswa.2026.132042_bib0016","series-title":"Proceedings of the advances in neural information processing systems","first-page":"1","article-title":"Visual instruction tuning","author":"Liu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132042_bib0017","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization, arXiv preprint. arXiv: 1711.05101."},{"key":"10.1016\/j.eswa.2026.132042_bib0018","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3574\u20143580","article-title":"Senticap: Generating image descriptions with sentiments","author":"Mathews","year":"2016"},{"key":"10.1016\/j.eswa.2026.132042_bib0019","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8591","article-title":"Semstyle: Learning to generate stylised image captions using unaligned text","author":"Mathews","year":"2018"},{"key":"10.1016\/j.eswa.2026.132042_bib0020","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10870","article-title":"Spatio-temporal graph for video captioning with knowledge distillation","author":"Pan","year":"2020"},{"key":"10.1016\/j.eswa.2026.132042_bib0021","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"1029","article-title":"Hierarchical recurrent neural encoder for video representation with application to captioning","author":"Pan","year":"2016"},{"key":"10.1016\/j.eswa.2026.132042_bib0022","series-title":"Annual meeting of the association for computational linguistics","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.eswa.2026.132042_bib0023","series-title":"Proceedings of the 29th ACM international conference on multimedia","first-page":"4892","article-title":"Latent memory-augmented graph transformer for visual storytelling","author":"Qi","year":"2021"},{"key":"10.1016\/j.eswa.2026.132042_bib0024","series-title":"Proceedings of the 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.eswa.2026.132042_bib0025","first-page":"1","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"[Online]"},{"key":"10.1016\/j.eswa.2026.132042_bib0026","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2514","article-title":"Semantic grouping network for video captioning","author":"Ryu","year":"2021"},{"key":"10.1016\/j.eswa.2026.132042_bib0027","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"15558","article-title":"Accurate and fast compressed video captioning","author":"Shen","year":"2023"},{"key":"10.1016\/j.eswa.2026.132042_bib0028","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12516","article-title":"Engaging image captioning via personality","author":"Shuster","year":"2019"},{"key":"10.1016\/j.eswa.2026.132042_bib0029","doi-asserted-by":"crossref","first-page":"1858","DOI":"10.1109\/TMM.2022.3183402","article-title":"Contextual attention network for emotional video captioning","volume":"25","author":"Song","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132042_bib0030","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1109\/TIP.2024.3359045","article-title":"Emotional video captioning with vision-based emotion interpretation network","volume":"33","author":"Song","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132042_bib0031","series-title":"Proceedings of the ACM international conference on multimedia","first-page":"589","article-title":"Emotion-prior awareness network for emotional video captioning","author":"Song","year":"2023"},{"key":"10.1016\/j.eswa.2026.132042_bib0032","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., & Lacroix, T., et al. (2023a). Llama: Open and efficient foundation language models, arXiv preprint. arXiv: 2302.13971, (pp. 1\u201316)."},{"key":"10.1016\/j.eswa.2026.132042_bib0033","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., & Babaei, Y., et al. (2023b). Llama2: Open foundation and fine-tuned chat models, arXiv preprint. arXiv: 2307.09288, (pp. 1\u201345)."},{"key":"10.1016\/j.eswa.2026.132042_bib0034","series-title":"Companion proceedings of the web conference","first-page":"716","article-title":"Vinter: Image narrative generation with emotion-arc-aware transformer","author":"Uehara","year":"2022"},{"key":"10.1016\/j.eswa.2026.132042_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4566","article-title":"Cider: Consensus-based image description evaluation","author":"Vedantam","year":"2015"},{"key":"10.1016\/j.eswa.2026.132042_bib0036","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"4534","article-title":"Sequence to sequence-video to text","author":"Venugopalan","year":"2015"},{"key":"10.1016\/j.eswa.2026.132042_bib0037","series-title":"Proceedings of the conference of the north american chapter of the association for computational linguistics: Human language technologies","first-page":"1494","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"Venugopalan","year":"2015"},{"key":"10.1016\/j.eswa.2026.132042_bib0038","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2641","article-title":"Controllable video captioning with pos sequence guidance based on gated fusion network","author":"Wang","year":"2019"},{"key":"10.1016\/j.eswa.2026.132042_bib0039","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7622","article-title":"Reconstruction network for video captioning","author":"Wang","year":"2018"},{"key":"10.1016\/j.eswa.2026.132042_bib0040","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1109\/TMM.2021.3058555","article-title":"Emotion expression with fact transfer for video description","volume":"24","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132042_bib0041","first-page":"1","article-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.eswa.2026.132042_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13525","article-title":"Retrieval-augmented egocentric video captioning","author":"Xu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132042_bib0043","doi-asserted-by":"crossref","first-page":"1772","DOI":"10.1109\/TMM.2020.3002669","article-title":"Deep reinforcement polishing network for video captioning","volume":"23","author":"Xu","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132042_bib0044","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"19323","article-title":"Secap: Speech emotion captioning with large language model","author":"Xu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132042_bib0045","series-title":"Chinese conference on pattern recognition and computer vision","first-page":"368","article-title":"Clip meets video captioning: Concept-aware representation learning does matter","author":"Yang","year":"2022"},{"key":"10.1016\/j.eswa.2026.132042_bib0046","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3119","article-title":"Non-autoregressive coarse-to-fine video captioning","author":"Yang","year":"2021"},{"key":"10.1016\/j.eswa.2026.132042_bib0047","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"496","article-title":"Dual-path collaborative generation network for emotional video captioning","author":"Ye","year":"2024"},{"key":"10.1016\/j.eswa.2026.132042_bib0048","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"17939","article-title":"Hierarchical modular network for video captioning","author":"Ye","year":"2022"},{"key":"10.1016\/j.eswa.2026.132042_bib0049","unstructured":"Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., & Chen, S., et al. (2022). Opt: Open pre-trained transformer language models. arXiv: 2205.01068, (pp. 1\u201316)."},{"issue":"12","key":"10.1016\/j.eswa.2026.132042_bib0050","doi-asserted-by":"crossref","first-page":"3088","DOI":"10.1109\/TPAMI.2019.2920899","article-title":"Reconstruct and represent video contents for captioning via reinforcement learning","volume":"42","author":"Zhang","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132042_bib0051","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13278","article-title":"Object relational graph with teacher-recommended learning for video captioning","author":"Zhang","year":"2020"},{"key":"10.1016\/j.eswa.2026.132042_bib0052","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18243","article-title":"Streaming dense video captioning","author":"Zhou","year":"2024"},{"key":"10.1016\/j.eswa.2026.132042_bib0053","series-title":"The international conference on learning representations","first-page":"1","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426009553?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426009553?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:10:44Z","timestamp":1781309444000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426009553"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":53,"alternative-id":["S0957417426009553"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132042","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"GLM-EER: Global-Local Memory and Emotion Evaluation Refinement For Emotional Video Description","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132042","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":"132042"}}