{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T13:26:58Z","timestamp":1787923618900,"version":"build-2784847793"},"reference-count":60,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002338","name":"Ministry of Education of the People's Republic of China","doi-asserted-by":"publisher","award":["IRT17R86"],"award-info":[{"award-number":["IRT17R86"]}],"id":[{"id":"10.13039\/501100002338","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172326"],"award-info":[{"award-number":["62172326"]}],"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":["62137002"],"award-info":[{"award-number":["62137002"]}],"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":["62302384"],"award-info":[{"award-number":["62302384"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M742790"],"award-info":[{"award-number":["2023M742790"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0117103"],"award-info":[{"award-number":["2022ZD0117103"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012455","name":"China Knowledge Centre for Engineering Sciences and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012455","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":[[2026,9]]},"DOI":"10.1016\/j.neunet.2026.108899","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T18:11:48Z","timestamp":1774462308000},"page":"108899","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["VLDUS: Vision-language distillated unseen synthesizer for zero-shot object detection"],"prefix":"10.1016","volume":"201","author":[{"given":"Caixia","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6614-1664","authenticated-orcid":false,"given":"Muyan","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2876-5563","authenticated-orcid":false,"given":"Nuohan","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weizhan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7888-0587","authenticated-orcid":false,"given":"Feng","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108899_bib0001","series-title":"Proceedings of the international conference on machine learning","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"Arjovsky","year":"2017"},{"key":"10.1016\/j.neunet.2026.108899_bib0002","series-title":"Proceedings of the european conference on computer vision","first-page":"384","article-title":"Zero-shot object detection","author":"Bansal","year":"2018"},{"key":"10.1016\/j.neunet.2026.108899_bib0003","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"6154","article-title":"Cascade r-cnn: Delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.1016\/j.neunet.2026.108899_bib0004","series-title":"International conference on machine learning","first-page":"4611","article-title":"Evolving semantic prototype improves generative zero-shot learning","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.108899_bib0005","unstructured":"Demirel, B., Cinbis, R. G., & Ikizler-Cinbis, N. (2018). Zero-shot object detection by hybrid region embedding. arXiv: 1805.06157\">arXiv: 1805.06157."},{"key":"10.1016\/j.neunet.2026.108899_bib0006","unstructured":"Du, Y., Liu, Z., Li, J., & Zhao, W. X. (2022). A survey of vision-language pre-trained models. arXiv: 2202.10936\">arXiv: 2202.10936."},{"key":"10.1016\/j.neunet.2026.108899_bib0007","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.108899_bib0008","series-title":"Proceedings of the European conference on computer vision","first-page":"21","article-title":"Multi-modal cycle-consistent generalized zero-shot learning","author":"Felix","year":"2018"},{"issue":"6","key":"10.1016\/j.neunet.2026.108899_bib0009","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","volume":"129","author":"Gou","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.108899_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11020","article-title":"Online knowledge distillation via collaborative learning","author":"Guo","year":"2020"},{"key":"10.1016\/j.neunet.2026.108899_bib0011","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","article-title":"A multi-space approach to zero-shot object detection","author":"Gupta","year":"2020"},{"key":"10.1016\/j.neunet.2026.108899_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2371","article-title":"Contrastive embedding for generalized zero-shot learning","author":"Han","year":"2021"},{"key":"10.1016\/j.neunet.2026.108899_bib0013","series-title":"Proceedings of the asian conference on computer vision","article-title":"Synthesizing the unseen for zero-shot object detection","author":"Hayat","year":"2020"},{"key":"10.1016\/j.neunet.2026.108899_bib0014","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.108899_bib0015","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9570","article-title":"Cross domain object detection by target-perceived dual branch distillation","author":"He","year":"2022"},{"key":"10.1016\/j.neunet.2026.108899_bib0016","first-page":"1","article-title":"Enhancing mid\u2013low-resolution ship detection with high-resolution feature distillation","volume":"19","author":"He","year":"2021","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.1016\/j.neunet.2026.108899_bib0017","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv: 1503.02531\">arXiv: 1503.02531."},{"key":"10.1016\/j.neunet.2026.108899_bib0018","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23627","article-title":"Visual-augmented dynamic semantic prototype for generative zero-shot learning","author":"Hou","year":"2024"},{"key":"10.1016\/j.neunet.2026.108899_bib0019","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7622","article-title":"Robust region feature synthesizer for zero-shot object detection","author":"Huang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108899_bib0020","first-page":"1","article-title":"M-RRFS: A memory-based robust region feature synthesizer for zero-shot object detection","author":"Huang","year":"2024","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.108899_bib0021","series-title":"Proceedings of the international conference on intelligent autonomous systems","first-page":"8","article-title":"Research on object detection network based on knowledge distillation","author":"Kuang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108899_bib0022","series-title":"Proceedings of the IEEE international conference on robotics and automation","first-page":"9267","article-title":"Zero-shot object detection based on dynamic semantic vectors","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.108899_bib0023","series-title":"Proceedings of the ACM international conference on multimedia","first-page":"1587","article-title":"Alleviating feature confusion for generative zero-shot learning","author":"Li","year":"2019"},{"key":"10.1016\/j.neunet.2026.108899_bib0024","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.isprsjprs.2019.11.023","article-title":"Object detection in optical remote sensing images: A survey and a new benchmark","volume":"159","author":"Li","year":"2020","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.108899_bib0025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2021.04.014","article-title":"Augmented semantic feature based generative network for generalized zero-shot learning","volume":"143","author":"Li","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108899_bib0026","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Zero-shot object detection with textual descriptions","author":"Li","year":"2019"},{"key":"10.1016\/j.neunet.2026.108899_bib0027","series-title":"Proceedings of the european conference on computer vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"issue":"10","key":"10.1016\/j.neunet.2026.108899_bib0028","doi-asserted-by":"crossref","first-page":"19016","DOI":"10.1109\/TITS.2022.3151073","article-title":"From less to more: Progressive generalized zero-shot detection with curriculum learning","volume":"23","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.108899_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106215","article-title":"Tolerant self-distillation for image classification","volume":"174","author":"Liu","year":"2024","journal-title":"Neural Networks"},{"issue":"11","key":"10.1016\/j.neunet.2026.108899_bib0030","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.108899_bib0031","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2085","article-title":"Styleclip: Text-driven manipulation of stylegan imagery","author":"Patashnik","year":"2021"},{"key":"10.1016\/j.neunet.2026.108899_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14443","article-title":"Multi-scale aligned distillation for low-resolution detection","author":"Qi","year":"2021"},{"key":"10.1016\/j.neunet.2026.108899_bib0033","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.neunet.2026.108899_bib0034","unstructured":"Rahman, S., Khan, S., & Barnes, N. (2018a). Polarity loss for zero-shot object detection. arXiv: 1811.08982\">arXiv: 1811.08982."},{"key":"10.1016\/j.neunet.2026.108899_bib0035","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6082","article-title":"Transductive learning for zero-shot object detection","author":"Rahman","year":"2019"},{"key":"10.1016\/j.neunet.2026.108899_bib0036","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11932","article-title":"Improved visual-semantic alignment for zero-shot object detection","author":"Rahman","year":"2020"},{"key":"10.1016\/j.neunet.2026.108899_bib0037","series-title":"Proceedings of the asian conference on computer vision","first-page":"547","article-title":"Zero-shot object detection: Learning to simultaneously recognize and localize novel concepts","author":"Rahman","year":"2018"},{"key":"10.1016\/j.neunet.2026.108899_bib0038","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18082","article-title":"Denseclip: Language-guided dense prediction with context-aware prompting","author":"Rao","year":"2022"},{"key":"10.1016\/j.neunet.2026.108899_bib0039","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108899_bib0040","unstructured":"Sarma, S., Kumar, S., & Sur, A. (2022). Resolving semantic confusions for improved zero-shot detection. arXiv: 2212.06097\">arXiv: 2212.06097."},{"issue":"4","key":"10.1016\/j.neunet.2026.108899_bib0041","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1016\/j.neuron.2012.11.001","article-title":"The future of memory: Remembering, imagining, and the brain","volume":"76","author":"Schacter","year":"2012","journal-title":"Neuron"},{"key":"10.1016\/j.neunet.2026.108899_bib0042","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.neunet.2023.04.015","article-title":"Multi-teacher knowledge distillation based on joint guidance of probe and adaptive corrector","volume":"164","author":"Shang","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108899_bib0043","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5445","article-title":"Saui: Scale-aware unseen imagineer for zero-shot object detection","author":"Wang","year":"2024"},{"key":"10.1016\/j.neunet.2026.108899_bib0044","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14090","article-title":"Improving weakly supervised visual grounding by contrastive knowledge distillation","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108899_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106324","article-title":"Contrastive prototype-guided generation for generalized zero-shot learning","volume":"176","author":"Wang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108899_bib0046","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"5542","article-title":"Feature generating networks for zero-shot learning","author":"Xian","year":"2018"},{"key":"10.1016\/j.neunet.2026.108899_bib0047","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3520","article-title":"Oriented r-CNN for object detection","author":"Xie","year":"2021"},{"issue":"5","key":"10.1016\/j.neunet.2026.108899_bib0048","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1049\/cvi2.12097","article-title":"Dd-yolo: An object detection method combining knowledge distillation and differentiable architecture search","volume":"16","author":"Xing","year":"2022","journal-title":"IET Computer Vision"},{"key":"10.1016\/j.neunet.2026.108899_bib0049","article-title":"Semantics-guided contrastive network for zero-shot object detection","author":"Yan","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108899_bib0050","doi-asserted-by":"crossref","first-page":"8163","DOI":"10.1109\/TIP.2020.3011807","article-title":"Semantics-preserving graph propagation for zero-shot object detection","volume":"29","author":"Yan","year":"2020","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108899_bib0051","doi-asserted-by":"crossref","first-page":"1325","DOI":"10.1109\/TMM.2021.3063616","article-title":"Alleviating domain shift via discriminative learning for generalized zero-shot learning","volume":"24","author":"Ye","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.108899_bib0052","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2023.106092","article-title":"Trainable spiking-YOLO for low-latency and high-performance object detection","volume":"172","author":"Yuan","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108899_bib0053","article-title":"Vision-language models for vision tasks: A survey","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108899_bib0054","series-title":"Proceedings of the international joint conferences on artificial intelligence","article-title":"Zero-shot object detection via learning an embedding from semantic space to visual space","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.108899_bib0055","series-title":"Proceedings of the international joint conference on neural networks","first-page":"1","article-title":"Zero-shot object detection with textual descriptions using convolutional neural networks","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.108899_bib0056","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12967","article-title":"Gtnet: Generative transfer network for zero-shot object detection","author":"Zhao","year":"2020"},{"key":"10.1016\/j.neunet.2026.108899_bib0057","series-title":"Proceedings of the asian conference on computer vision","article-title":"Background learnable cascade for zero-shot object detection","author":"Zheng","year":"2020"},{"key":"10.1016\/j.neunet.2026.108899_bib0058","article-title":"Synthesizing knowledge-enhanced features for real-world zero-shot food detection","author":"Zhou","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108899_bib0059","series-title":"Proceedings of the ACM international conference on multimedia","article-title":"SeeDS: Semantic separable diffusion synthesizer for zero-shot food detection","author":"Zhou","year":"2023"},{"key":"10.1016\/j.neunet.2026.108899_bib0060","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11693","article-title":"Don\u2019T even look once: Synthesizing features for zero-shot detection","author":"Zhu","year":"2020"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003606?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003606?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T12:42:37Z","timestamp":1787920957000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026003606"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":60,"alternative-id":["S0893608026003606"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108899","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"VLDUS: Vision-language distillated unseen synthesizer for zero-shot object detection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108899","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":"108899"}}