{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:21:53Z","timestamp":1783635713134,"version":"3.55.0"},"reference-count":54,"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\/501100003399","name":"Shanghai Municipality Science and Technology Commission","doi-asserted-by":"publisher","award":["25511107200"],"award-info":[{"award-number":["25511107200"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472178"],"award-info":[{"award-number":["62472178"]}],"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":["62572059"],"award-info":[{"award-number":["62572059"]}],"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":["62376271"],"award-info":[{"award-number":["62376271"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017622","name":"Shenzhen Research and Development Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017622","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"publisher","award":["CJGJZD20240729141906008"],"award-info":[{"award-number":["CJGJZD20240729141906008"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Jiangxi Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["20253BAC280104"],"award-info":[{"award-number":["20253BAC280104"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.knosys.2026.116323","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:20:18Z","timestamp":1780586418000},"page":"116323","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MEDP: Multimodal-Enhanced Dynamic Prototype learning for few-shot dynamic scene graph generation"],"prefix":"10.1016","volume":"348","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1579-2891","authenticated-orcid":false,"given":"Xuejiao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3406-9882","authenticated-orcid":false,"given":"Ziheng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiliang","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changbo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8365-0970","authenticated-orcid":false,"given":"Gaoqi","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116323_b1","doi-asserted-by":"crossref","unstructured":"G. Wang, Z. Li, Q. Chen, Y. Liu, Oed: Towards one-stage end-to-end dynamic scene graph generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 27938\u201327947.","DOI":"10.1109\/CVPR52733.2024.02639"},{"key":"10.1016\/j.knosys.2026.116323_b2","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.patrec.2023.04.014","article-title":"Question-aware dynamic scene graph of local semantic representation learning for visual question answering","volume":"170","author":"Wu","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.knosys.2026.116323_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112629","article-title":"Robust visual question answering utilizing bias instances and label imbalance","volume":"305","author":"Zhao","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116323_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112827","article-title":"R-vqa: A robust visual question answering model","volume":"309","author":"Chowdhury","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116323_b5","doi-asserted-by":"crossref","first-page":"4995","DOI":"10.1007\/s40747-023-00998-5","article-title":"Lightweight dense video captioning with cross-modal attention and knowledge-enhanced unbiased scene graph","volume":"9","author":"Han","year":"2023","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.knosys.2026.116323_b6","doi-asserted-by":"crossref","first-page":"2004","DOI":"10.1109\/TIP.2022.3148868","article-title":"Adversarial reinforcement learning with object-scene relational graph for video captioning","volume":"31","author":"Hua","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116323_b7","series-title":"Compositional video synthesis with action graphs","author":"Bar","year":"2020"},{"key":"10.1016\/j.knosys.2026.116323_b8","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1109\/JSTSP.2023.3323654","article-title":"Vr+hd: Video semantic reconstruction from spatio-temporal scene graphs","volume":"17","author":"Li","year":"2023","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.knosys.2026.116323_b9","doi-asserted-by":"crossref","unstructured":"Y. Cong, W. Liao, H. Ackermann, B. Rosenhahn, M.Y. Yang, Spatial-temporal transformer for dynamic scene graph generation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 16372\u201316382.","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"10.1016\/j.knosys.2026.116323_b10","series-title":"Td2-net: Toward denoising and debiasing for dynamic scene graph generation","author":"Lin","year":"2024"},{"key":"10.1016\/j.knosys.2026.116323_b11","doi-asserted-by":"crossref","unstructured":"Y. Li, X. Yang, C. Xu, Dynamic scene graph generation via anticipatory pre-training, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 13874\u201313883.","DOI":"10.1109\/CVPR52688.2022.01350"},{"key":"10.1016\/j.knosys.2026.116323_b12","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22803","article-title":"Unbiased scene graph generation in videos","author":"Nag","year":"2023"},{"key":"10.1016\/j.knosys.2026.116323_b13","doi-asserted-by":"crossref","unstructured":"S. Wang, L. Gao, X. Lyu, Y. Guo, P. Zeng, J. Song, Dynamic scene graph generation via temporal prior inference, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 5793\u20135801.","DOI":"10.1145\/3503161.3548324"},{"key":"10.1016\/j.knosys.2026.116323_b14","article-title":"Spatial-temporal knowledge-embedded transformer for video scene graph generation","author":"Pu","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116323_b15","doi-asserted-by":"crossref","unstructured":"J. Lu, L. Chen, Y. Song, S. Lin, C. Wang, G. He, Prior knowledge-driven dynamic scene graph generation with causal inference, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 4877\u20134885.","DOI":"10.1145\/3581783.3612249"},{"key":"10.1016\/j.knosys.2026.116323_b16","doi-asserted-by":"crossref","unstructured":"J. Xing, M. Wang, Y. Liu, B. Mu, Revisiting the spatial and temporal modeling for few-shot action recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2023, pp. 3001\u20133009.","DOI":"10.1609\/aaai.v37i3.25403"},{"key":"10.1016\/j.knosys.2026.116323_b17","doi-asserted-by":"crossref","unstructured":"X. Wang, S. Zhang, Z. Qing, C. Gao, Y. Zhang, D. Zhao, N. Sang, Molo: Motion-augmented long-short contrastive learning for few-shot action recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18011\u201318021.","DOI":"10.1109\/CVPR52729.2023.01727"},{"key":"10.1016\/j.knosys.2026.116323_b18","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"Snell","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116323_b19","doi-asserted-by":"crossref","unstructured":"H. Tang, J. Liu, S. Yan, R. Yan, Z. Li, J. Tang, M3net: multi-view encoding, matching, and fusion for few-shot fine-grained action recognition, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 1719\u20131728.","DOI":"10.1145\/3581783.3612221"},{"key":"10.1016\/j.knosys.2026.116323_b20","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.knosys.2026.116323_b21","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116323_b22","doi-asserted-by":"crossref","unstructured":"C. Liu, Y. Jin, K. Xu, G. Gong, Y. Mu, Beyond short-term snippet: Video relation detection with spatio-temporal global context, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10840\u201310849.","DOI":"10.1109\/CVPR42600.2020.01085"},{"key":"10.1016\/j.knosys.2026.116323_b23","doi-asserted-by":"crossref","unstructured":"K. Gao, L. Chen, Y. Niu, J. Shao, J. Xiao, Classification-then-grounding: Reformulating video scene graphs as temporal bipartite graphs, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 19497\u201319506.","DOI":"10.1109\/CVPR52688.2022.01889"},{"key":"10.1016\/j.knosys.2026.116323_b24","series-title":"2023 IEEE International Conference on Robotics and Automation","first-page":"8231","article-title":"Cross-modality time-variant relation learning for generating dynamic scene graphs","author":"Wang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116323_b25","doi-asserted-by":"crossref","unstructured":"M. Chen, L. Li, W. Wang, Y. Yang, Diffvsgg: Diffusion-driven online video scene graph generation, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 29161\u201329172.","DOI":"10.1109\/CVPR52734.2025.02715"},{"key":"10.1016\/j.knosys.2026.116323_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113218","article-title":"Learning prototypes from background and latent objects for few-shot semantic segmentation","volume":"314","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116323_b27","article-title":"LLM knowledge-driven target prototype learning for few-shot segmentation","author":"Li","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116323_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113288","article-title":"Knowledge-based natural answer generation via effective graph learning","volume":"316","author":"Liu","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116323_b29","doi-asserted-by":"crossref","unstructured":"Z.X. Ma, Z.D. Chen, L.J. Zhao, Z.C. Zhang, X. Luo, X.S. Xu, Cross-layer and cross-sample feature optimization network for few-shot fine-grained image classification, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2024, pp. 4136\u20134144.","DOI":"10.1609\/aaai.v38i5.28208"},{"key":"10.1016\/j.knosys.2026.116323_b30","first-page":"1","article-title":"A data augmented method for plant disease leaf image recognition based on enhanced gan model network","volume":"2","author":"Xin","year":"2023","journal-title":"J. Inform. Web Eng."},{"key":"10.1016\/j.knosys.2026.116323_b31","doi-asserted-by":"crossref","first-page":"4594","DOI":"10.1109\/TIP.2019.2910052","article-title":"Multi-level semantic feature augmentation for one-shot learning","volume":"28","author":"Chen","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116323_b32","series-title":"Decomposed prototype learning for few-shot scene graph generation","author":"Li","year":"2023"},{"key":"10.1016\/j.knosys.2026.116323_b33","doi-asserted-by":"crossref","first-page":"12350","DOI":"10.1109\/TKDE.2023.3270311","article-title":"A comprehensive survey on multi-view clustering","volume":"35","author":"Fang","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2026.116323_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110110","article-title":"Hyrsm++: Hybrid relation guided temporal set matching for few-shot action recognition","volume":"147","author":"Wang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116323_b35","article-title":"Generalized semantic contrastive learning via embedding side information for few-shot object detection","author":"Chen","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116323_b36","doi-asserted-by":"crossref","unstructured":"Z. Li, Y. Wang, K. Li, Fewvs: A vision-semantics integration framework for few-shot image classification, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 1341\u20131350.","DOI":"10.1145\/3664647.3681427"},{"key":"10.1016\/j.knosys.2026.116323_b37","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.knosys.2026.116323_b38","doi-asserted-by":"crossref","unstructured":"L. Chen, X. Wang, J. Lu, S. Lin, C. Wang, G. He, Clip-driven open-vocabulary 3d scene graph generation via cross-modality contrastive learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 27863\u201327873.","DOI":"10.1109\/CVPR52733.2024.02632"},{"key":"10.1016\/j.knosys.2026.116323_b39","doi-asserted-by":"crossref","unstructured":"S. Koch, N. Vaskevicius, M. Colosi, P. Hermosilla, T. Ropinski, Open3dsg: Open-vocabulary 3d scene graphs from point clouds with queryable objects and open-set relationships, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 14183\u201314193.","DOI":"10.1109\/CVPR52733.2024.01345"},{"key":"10.1016\/j.knosys.2026.116323_b40","doi-asserted-by":"crossref","unstructured":"Y. Zhang, Y. Pan, T. Yao, R. Huang, T. Mei, C.W. Chen, Learning to generate language-supervised and open-vocabulary scene graph using pre-trained visual-semantic space, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 2915\u20132924.","DOI":"10.1109\/CVPR52729.2023.00285"},{"key":"10.1016\/j.knosys.2026.116323_b41","doi-asserted-by":"crossref","unstructured":"R. Li, S. Zhang, D. Lin, K. Chen, X. He, From pixels to graphs: Open-vocabulary scene graph generation with vision-language models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 28076\u201328086.","DOI":"10.1109\/CVPR52733.2024.02652"},{"key":"10.1016\/j.knosys.2026.116323_b42","doi-asserted-by":"crossref","unstructured":"Q. Yu, J. Li, Y. Wu, S. Tang, W. Ji, Y. Zhuang, Visually-prompted language model for fine-grained scene graph generation in an open world, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 21560\u201321571.","DOI":"10.1109\/ICCV51070.2023.01971"},{"key":"10.1016\/j.knosys.2026.116323_b43","unstructured":"K. Gao, L. Chen, H. Zhang, J. Xiao, Q. Sun, Compositional prompt tuning with motion cues for open-vocabulary video relation detection, in: Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda, 2023, pp. 1\u20135."},{"key":"10.1016\/j.knosys.2026.116323_b44","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"29150","article-title":"Hyperglm: Hypergraph for video scene graph generation and anticipation","author":"Nguyen","year":"2025"},{"key":"10.1016\/j.knosys.2026.116323_b45","doi-asserted-by":"crossref","unstructured":"S. Wu, H. Fei, T.S. Chua, Universal scene graph generation, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 14158\u201314168.","DOI":"10.1109\/CVPR52734.2025.01321"},{"key":"10.1016\/j.knosys.2026.116323_b46","doi-asserted-by":"crossref","unstructured":"D. Yang, M. Kim, S. Mac Kim, B.w. Kwak, M. Park, J. Hong, W. Woo, J. Yeo, LLM meets scene graph: Can large language models understand and generate scene graphs? a benchmark and empirical study, in: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025, pp. 21335\u201321360.","DOI":"10.18653\/v1\/2025.acl-long.1036"},{"key":"10.1016\/j.knosys.2026.116323_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111992","article-title":"Scenellm: Implicit language reasoning in llm for dynamic scene graph generation","volume":"170","author":"Zhang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116323_b48","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116323_b49","article-title":"Effectiveness of entropy weight method in decision-making","volume":"2020","author":"Zhu","year":"2020","journal-title":"Math. Probl. Eng."},{"key":"10.1016\/j.knosys.2026.116323_b50","doi-asserted-by":"crossref","unstructured":"J. Ji, R. Krishna, L. Fei-Fei, J.C. Niebles, Action genome: Actions as compositions of spatio-temporal scene graphs, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10236\u201310247.","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"10.1016\/j.knosys.2026.116323_b51","doi-asserted-by":"crossref","unstructured":"K. Tang, H. Zhang, B. Wu, W. Luo, W. Liu, Learning to compose dynamic tree structures for visual contexts, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 6619\u20136628.","DOI":"10.1109\/CVPR.2019.00678"},{"key":"10.1016\/j.knosys.2026.116323_b52","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.knosys.2026.116323_b53","doi-asserted-by":"crossref","unstructured":"J. Zhang, K.J. Shih, A. Elgammal, A. Tao, B. Catanzaro, Graphical contrastive losses for scene graph parsing, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11535\u201311543.","DOI":"10.1109\/CVPR.2019.01180"},{"key":"10.1016\/j.knosys.2026.116323_b54","doi-asserted-by":"crossref","unstructured":"Y. Teng, L. Wang, Z. Li, G. Wu, Target adaptive context aggregation for video scene graph generation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13688\u201313697.","DOI":"10.1109\/ICCV48922.2021.01343"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512601049X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512601049X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:04:31Z","timestamp":1783634671000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095070512601049X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":54,"alternative-id":["S095070512601049X"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116323","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MEDP: Multimodal-Enhanced Dynamic Prototype learning for few-shot dynamic scene graph generation","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116323","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116323"}}