{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T13:10:50Z","timestamp":1778764250677,"version":"3.51.4"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100007928","name":"Ningbo Science and Technology Bureau","doi-asserted-by":"publisher","award":["2024Z120"],"award-info":[{"award-number":["2024Z120"]}],"id":[{"id":"10.13039\/501100007928","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007928","name":"Ningbo Science and Technology Bureau","doi-asserted-by":"publisher","award":["2025Z053"],"award-info":[{"award-number":["2025Z053"]}],"id":[{"id":"10.13039\/501100007928","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neunet.2026.108773","type":"journal-article","created":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:18:34Z","timestamp":1771978714000},"page":"108773","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["KE-VUM: Knowledge-enhanced video understanding model for fine-grained movie description"],"prefix":"10.1016","volume":"199","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2889-2033","authenticated-orcid":false,"given":"Xiaojing","family":"Gu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7099-5093","authenticated-orcid":false,"given":"Gen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8332-5539","authenticated-orcid":false,"given":"Xiaolu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2189-4886","authenticated-orcid":false,"given":"Yijie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8958-6017","authenticated-orcid":false,"given":"Jiangjian","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108773_bib0001","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S. et al. (2023). Gpt-4 technical report. arXiv: 2303.08774."},{"key":"10.1016\/j.neunet.2026.108773_bib0002","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: A visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108773_bib0003","unstructured":"Ataallah, K., Shen, X., Abdelrahman, E., Sleiman, E., Zhu, D., Ding, J., & Elhoseiny, M. (2024). Minigpt4-video: Advancing multimodal llms for video understanding with interleaved visual-textual tokens. arXiv: 2404.03413."},{"key":"10.1016\/j.neunet.2026.108773_bib0004","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.neunet.2026.108773_bib0005","unstructured":"Bang, Y., Cahyawijaya, S., Lee, N., Dai, W., Su, D., Wilie, B., Lovenia, H., Ji, Z., Yu, T., Chung, W., bibinfoauthor Do, Q. W., bibinfoauthor Xu, Y., bibinfoauthor Fung, P. (2023). A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv: 2302.04023."},{"key":"10.1016\/j.neunet.2026.108773_bib0006","unstructured":"Baumel, T., Eyal, M., & Elhadad, M. (2018). Query focused abstractive summarization: Incorporating query relevance, multi-document coverage, and summary length constraints into seq2seq models. arXiv: 1801.07704."},{"key":"10.1016\/j.neunet.2026.108773_bib0007","doi-asserted-by":"crossref","first-page":"373","DOI":"10.2478\/jaiscr-2024-0020","article-title":"Exponential state estimation for delayed competitive neural network via stochastic sampled-data control with markov jump parameters under actuator failure","volume":"14","author":"Cao","year":"2024","journal-title":"Journal of Artificial Intelligence and Soft Computing Research"},{"key":"10.1016\/j.neunet.2026.108773_bib0008","unstructured":"Chan, C.-M., Xu, C., Yuan, R., Luo, H., Xue, W., Guo, Y., & Fu, J. (2024). Rq-rag: Learning to refine queries for retrieval augmented generation. arXiv: 2404.00610."},{"key":"10.1016\/j.neunet.2026.108773_bib0009","doi-asserted-by":"crossref","first-page":"72842","DOI":"10.52202\/075280-3185","article-title":"Vast: A vision-audio-subtitle-text omni-modality foundation model and dataset","volume":"36","author":"Chen","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108773_bib0010","unstructured":"Cheng, Z., Leng, S., Zhang, H., Xin, Y., Li, X., Chen, G., Zhu, Y., Zhang, W., Luo, Z., Zhao, D., Bing, L. (2024). Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms. arXiv: 2406.07476."},{"key":"10.1016\/j.neunet.2026.108773_bib0011","unstructured":"Fan, T., Wang, J., Ren, X., & Huang, C. (2025). MiniRAG: Towards extremely simple retrieval-augmented generation. arXiv: 2501.06713."},{"key":"10.1016\/j.neunet.2026.108773_bib0012","unstructured":"Ganesan, K. (2018). Rouge 2.0: Updated and improved measures for evaluation of summarization tasks. arXiv: 1803.01937."},{"key":"10.1016\/j.neunet.2026.108773_bib0013","unstructured":"Guo, Z., Xia, L., Yu, Y., Ao, T., & Huang, C. (2024). Lightrag: Simple and fast retrieval-augmented generation. 2, 3. arXiv: 2410.05779."},{"key":"10.1016\/j.neunet.2026.108773_bib0014","doi-asserted-by":"crossref","first-page":"2168","DOI":"10.1109\/TMM.2024.3521729","article-title":"Vlab: Enhancing video language pre-training by feature adapting and blending","volume":"27","author":"He","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.108773_bib0015","series-title":"Computer vision\u2013ECCV 2020: 16th european conference, glasgow, UK, august 23\u201328, 2020, proceedings, part IV 16","first-page":"709","article-title":"Movienet: A holistic dataset for movie understanding","author":"Huang","year":"2020"},{"key":"10.1016\/j.neunet.2026.108773_bib0016","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18198","article-title":"Video recap: Recursive captioning of hour-long videos","author":"Islam","year":"2024"},{"key":"10.1016\/j.neunet.2026.108773_bib0017","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13700","article-title":"Chat-univi: Unified visual representation empowers large language models with image and video understanding","author":"Jin","year":"2024"},{"key":"10.1016\/j.neunet.2026.108773_bib0018","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108773_bib0019","unstructured":"Li, F., Zhang, R., Zhang, H., Zhang, Y., Li, B., Li, W., Ma, Z., & Li, C. (2024a). Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. arXiv: 2407.07895."},{"key":"10.1016\/j.neunet.2026.108773_bib0020","unstructured":"Li, K., He, Y., Wang, Y., Li, Y., Wang, W., Luo, P., Wang, Y., Wang, L., & Qiao, Y. (2023). Videochat: Chat-centric video understanding. arXiv: 2305.06355."},{"key":"10.1016\/j.neunet.2026.108773_bib0021","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"22195","article-title":"Mvbench: A comprehensive multi-modal video understanding benchmark","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2026.108773_bib0022","unstructured":"Li, X., Wang, Y., Yu, J., Zeng, X., Huang, Y. Z., Gao, J., Li, K., He, Y., Wang, C., Qiao, Y., Wang, Y., Wang, L. (2024c). Videochat-flash: Hierarchical compression for long-context video modeling. arXiv: 2501.00574."},{"key":"10.1016\/j.neunet.2026.108773_bib0023","unstructured":"Li, Y., Chen, X., Hu, B., Wang, L., Shi, H., & Zhang, M. (2024d). Videovista: A versatile benchmark for video understanding and reasoning. arXiv: 2406.11303."},{"key":"10.1016\/j.neunet.2026.108773_bib0024","series-title":"European conference on computer vision","first-page":"323","article-title":"Llama-vid: An image is worth 2 tokens in large language models","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2026.108773_bib0025","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.neunet.2026.108773_bib0026","unstructured":"Ma, S., Xu, C., Jiang, X., Qu, M. L., & Guo, J. (2024). Think-on-graph 2.0: Deep and interpretable large language model reasoning with knowledge graph-guided retrieval. arXiv: 2407.10805."},{"key":"10.1016\/j.neunet.2026.108773_bib0027","unstructured":"Maaz, M., Rasheed, H., Khan, S., & Khan, F. S. (2023). Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv: 2306.05424."},{"issue":"9","key":"10.1016\/j.neunet.2026.108773_bib0028","doi-asserted-by":"crossref","DOI":"10.3390\/bdcc8090115","article-title":"Qa-rag: Exploring llm reliance on external knowledge","volume":"8","author":"Mansurova","year":"2024","journal-title":"Big Data and Cognitive Computing"},{"key":"10.1016\/j.neunet.2026.108773_bib0029","series-title":"Proceedings of the 40th 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.neunet.2026.108773_bib0030","series-title":"European conference on computer vision","first-page":"1","article-title":"Videomamba: Spatio-temporal selective state space model","author":"Park","year":"2024"},{"key":"10.1016\/j.neunet.2026.108773_bib0031","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.neunet.2026.108773_bib0032","unstructured":"Ren, X., Xu, L., Xia, L., Wang, S., Yin, D., & Huang, C. (2025). VideoRAG: Retrieval-augmented generation with extreme long-context videos. arXiv: 2502.01549."},{"key":"10.1016\/j.neunet.2026.108773_bib0033","doi-asserted-by":"crossref","unstructured":"Shu, Y., Zhang, P., Liu, Z., Qin, M., Zhou, J., Huang, T., & Zhao, B. (2024). Video-xl: Extra-long vision language model for hour-scale video understanding. arXiv: 2409.14485.","DOI":"10.1109\/CVPR52734.2025.02436"},{"key":"10.1016\/j.neunet.2026.108773_bib0034","unstructured":"Singh, I. S., Aggarwal, R., Allahverdiyev, I., Taha, M., Akalin, A., Zhu, K., & O\u2019Brien, S. (2024). ChunkRAG: Novel LLM-chunk filtering method for RAG systems. arXiv: 2410.19572."},{"key":"10.1016\/j.neunet.2026.108773_bib0035","unstructured":"Song, Z., Wang, C., Sheng, J., Zhang, C., Yu, G., Fan, J., & Chen, T. (2024). Moviellm: Enhancing long video understanding with AI-generated movies. arXiv: 2403.01422."},{"key":"10.1016\/j.neunet.2026.108773_bib0036","first-page":"1","article-title":"Robust dissipative sliding mode control synchronization of memristive inertial competitive neural networks with time-varying delay","author":"Subhashri","year":"2025","journal-title":"The European Physical Journal Special Topics"},{"key":"10.1016\/j.neunet.2026.108773_bib0037","unstructured":"G. Team, Anil, R., Borgeaud, S., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A. M., Hauth, A., Millican, K. et al. (2023). Gemini: A family of highly capable multimodal models. arXiv: 2312.11805."},{"key":"10.1016\/j.neunet.2026.108773_bib0038","unstructured":"G. Team, Georgiev, P., Lei, V. I., Burnell, R., Bai, L., Gulati, A., Vincent, G. T., Pan, Z., Wang, S. et al. (2024). Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv: 2403.05530."},{"key":"10.1016\/j.neunet.2026.108773_bib0039","doi-asserted-by":"crossref","unstructured":"Wang, J., Liang, Y., Meng, F., Sun, Z., Shi, H., Li, Z., Xu, J., Qu, J., & Zhou, J. (2023). Is chatgpt a good nlg evaluator? A preliminary study. arXiv: 2303.04048.","DOI":"10.18653\/v1\/2023.newsum-1.1"},{"key":"10.1016\/j.neunet.2026.108773_bib0040","unstructured":"Wang, J., Yuan, L., Zhang, Y., & Sun, H. (2024a). Tarsier: Recipes for training and evaluating large video description models. arXiv: 2407.00634."},{"key":"10.1016\/j.neunet.2026.108773_bib0041","series-title":"European conference on computer vision","first-page":"58","article-title":"Videoagent: Long-form video understanding with large language model as agent","author":"Wang","year":"2024"},{"key":"10.1016\/j.neunet.2026.108773_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1884","article-title":"Towards long-form video understanding","author":"Wu","year":"2021"},{"issue":"1","key":"10.1016\/j.neunet.2026.108773_bib0043","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108773_bib0044","unstructured":"Xu, L., Zhao, Y., Zhou, D., Lin, Z., Ng, S. K., & Feng, J. (2024). Pllava: Parameter-free llava extension from images to videos for video dense captioning. arXiv: 2404.16994."},{"key":"10.1016\/j.neunet.2026.108773_bib0045","unstructured":"Zhang, B., Li, K., Cheng, Z., Hu, Z., Yuan, Y., Chen, G., Leng, S., Jiang, Y., Zhang, H., Li, X., Jin, P., Zhang, W., Wang, F., Bing, L., Zhao, D. (2025). VideoLLaMA 3: Frontier multimodal foundation models for image and video understanding. arXiv: 2501.13106."},{"key":"10.1016\/j.neunet.2026.108773_bib0046","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., & Bing, L. (2023). Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv: 2306.02858.","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"10.1016\/j.neunet.2026.108773_bib0047","unstructured":"Zhang, P., Zhang, K., Li, B., Zeng, G., Yang, J., Zhang, Y., Wang, Z., Tan, H., Li, C., & Liu, Z. (2024). Long context transfer from language to vision. arXiv: 2406.16852."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002352?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002352?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:39:33Z","timestamp":1778762373000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026002352"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":47,"alternative-id":["S0893608026002352"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108773","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"KE-VUM: Knowledge-enhanced video understanding model for fine-grained movie description","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108773","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":"108773"}}