{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:04:42Z","timestamp":1790111082974,"version":"4.0.1"},"reference-count":72,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004826","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":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109384","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:41:28Z","timestamp":1783921288000},"page":"109384","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["FreeScene: Generative-enhanced visual modeling for generalized zero-shot image retrieval with scene sketches"],"prefix":"10.1016","volume":"205","author":[{"given":"Ran","family":"Zuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3379-8843","authenticated-orcid":false,"given":"Zhengming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxu","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2489-8113","authenticated-orcid":false,"given":"Zitan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingzhe","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7985-5743","authenticated-orcid":false,"given":"Wenwen","family":"Qiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109384_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.2026.109384_bib0002","series-title":"Convex optimization","author":"Boyd","year":"2004"},{"key":"10.1016\/j.neunet.2026.109384_bib0003","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109384_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2940","article-title":"Learning aligned cross-modal representations from weakly aligned data","author":"Castrejon","year":"2016"},{"key":"10.1016\/j.neunet.2026.109384_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107848","article-title":"EEG emotion copilot: Optimizing lightweight LLMs for emotional EEG interpretation with assisted medical record generation","volume":"192","author":"Chen","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109384_bib0006","unstructured":"Chen, Z., Duan, Y., Wang, W., He, J., Lu, T., Dai, J., & Qiao, Y. (2022). Vision transformer adapter for dense predictions. arXiv: 2205.08534."},{"key":"10.1016\/j.neunet.2026.109384_bib0007","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2395","article-title":"Partially does it: Towards scene-level fg-sbir with partial input","author":"Chowdhury","year":"2022"},{"key":"10.1016\/j.neunet.2026.109384_bib0008","series-title":"Proceedings of the european conference on computer vision","first-page":"253","article-title":"FS-coco: Towards understanding of freehand sketches of common objects in context","author":"Chowdhury","year":"2022"},{"key":"10.1016\/j.neunet.2026.109384_bib0009","unstructured":"Demi\u0107, E., & Zajc, L. \u010c. (2025). Back to the drawing board: Rethinking scene-level sketch-based image retrieval. arXiv: 2509.06566."},{"key":"10.1016\/j.neunet.2026.109384_bib0010","unstructured":"van den, O. A., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv: 1807.03748."},{"key":"10.1016\/j.neunet.2026.109384_bib0011","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2179","article-title":"Doodle to search: Practical zero-shot sketch-based image retrieval","author":"Dey","year":"2019"},{"key":"10.1016\/j.neunet.2026.109384_bib0012","article-title":"Pmte-llm: An llm-based time series forecasting method using professional mechanism and training experience","volume":"196","author":"Du","year":"2025","journal-title":"Neural Networks"},{"issue":"10","key":"10.1016\/j.neunet.2026.109384_bib0013","doi-asserted-by":"crossref","first-page":"2684","DOI":"10.1007\/s11263-020-01350-x","article-title":"Semantically tied paired cycle consistency for any-shot sketch-based image retrieval","volume":"128","author":"Dutta","year":"2020","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109384_bib0014","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5174","article-title":"Sketchycoco: Image generation from freehand scene sketches","author":"Gao","year":"2020"},{"key":"10.1016\/j.neunet.2026.109384_bib0015","unstructured":"Gao, L., Jiao, B., Wang, P., Zhang, S., Zhang, H., & Zhang, Y. (2024). Dual-modal prompting for sketch-based image retrieval. arXiv: 2404.18695."},{"key":"10.1016\/j.neunet.2026.109384_bib0016","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"650","article-title":"Scene-level sketch-based image retrieval with minimal pairwise supervision","volume":"vol. 37","author":"Ge","year":"2023"},{"key":"10.1016\/j.neunet.2026.109384_bib0017","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"7678","article-title":"Semi-transductive learning for generalized zero-shot sketch-based image retrieval","volume":"vol. 37","author":"Ge","year":"2023"},{"key":"10.1016\/j.neunet.2026.109384_bib0018","unstructured":"Jiang, T., Song, M., Zhang, Z., Huang, H., Deng, W., Sun, F., Zhang, Q., Wang, D., & Zhuang, F. (2024). E5-v: Universal embeddings with multimodal large language models. arXiv: 2407.12580."},{"key":"10.1016\/j.neunet.2026.109384_bib0019","doi-asserted-by":"crossref","unstructured":"Jin, P., Li, H., Cheng, Z., Li, K., Ji, X., Liu, C., Yuan, L., & Chen, J. (2023). DiffusionRet: Generative text-video retrieval with diffusion model. arXiv: 2303.09867.","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"10.1016\/j.neunet.2026.109384_bib0020","doi-asserted-by":"crossref","first-page":"3657","DOI":"10.1109\/TIP.2022.3173815","article-title":"Augmented multimodality fusion for generalized zero-shot sketch-based visual retrieval","volume":"31","author":"Jing","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109384_bib0021","unstructured":"Kipf, T. N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv: 1609.02907."},{"key":"10.1016\/j.neunet.2026.109384_bib0022","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16859","article-title":"How to handle sketch-abstraction in sketch-based image retrieval?","author":"Koley","year":"2024"},{"key":"10.1016\/j.neunet.2026.109384_bib0023","unstructured":"Lei Ba, J., Kiros, J. R., & Hinton, G. E. (2016). Layer normalization. arXiv e-prints:1607."},{"key":"10.1016\/j.neunet.2026.109384_bib0024","doi-asserted-by":"crossref","first-page":"9735","DOI":"10.1109\/TMM.2025.3618570","article-title":"Multi-view knowledge guided semantic prototype learning for generalized zero-shot action recognition","volume":"27","author":"Li","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109384_bib0025","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"9554","article-title":"Dr. Clip: Clip-driven universal framework for zero-shot sketch image retrieval","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2026.109384_bib0026","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23349","article-title":"Zero-shot everything sketch-based image retrieval, and in explainable style","author":"Lin","year":"2023"},{"key":"10.1016\/j.neunet.2026.109384_bib0027","series-title":"Proceedings of the international conference on learning representations","article-title":"Universal multimodal retrieval with multimodal llms","author":"Lin","year":"2026"},{"key":"10.1016\/j.neunet.2026.109384_bib0028","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"},{"key":"10.1016\/j.neunet.2026.109384_bib0029","article-title":"Granger-TSLLM: Granger causality enhanced LLMs with residual-quantized tokenizer for multivariate time series forecasting","volume":"196","author":"Liu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109384_bib0030","article-title":"Symmetrical bidirectional knowledge alignment for zero-shot sketch-based image retrieval","volume":"193","author":"Liu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109384_bib0031","doi-asserted-by":"crossref","first-page":"3737","DOI":"10.1109\/TIP.2022.3175403","article-title":"Scenesketcher-v2: Fine-grained scene-level sketch-based image retrieval using adaptive GCNs","volume":"31","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109384_bib0032","series-title":"Proceedings of the european conference on computer vision","first-page":"718","article-title":"Scenesketcher: Fine-grained image retrieval with scene sketches","author":"Liu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109384_bib0033","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109384_bib0034","doi-asserted-by":"crossref","first-page":"12538","DOI":"10.1109\/TCSVT.2025.3585412","article-title":"Relation-aware meta-learning for zero-shot sketch-based image retrieval","volume":"35","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109384_bib0035","doi-asserted-by":"crossref","first-page":"10551","DOI":"10.1109\/TCSVT.2026.3666513","article-title":"Zero-shot sketch-based image retrieval via mixed species augmentation and bidirectional mining","volume":"36","author":"Liu","year":"2026","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109384_bib0036","article-title":"Zero-shot sketch-based image retrieval with teacher-guided and student-centered cross-modal bidirectional knowledge distillation","volume":"164","author":"Liu","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109384_bib0037","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Zhang, J., Qi, Z., Shan, Y., & Qie, X. (2023). T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv: 2302.08453.","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"10.1016\/j.neunet.2026.109384_bib0038","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.2026.109384_bib0039","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.neunet.2026.109384_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2765","article-title":"Clip for all things zero-shot sketch-based image retrieval, fine-grained or not","author":"Sain","year":"2023"},{"key":"10.1016\/j.neunet.2026.109384_bib0041","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6873","article-title":"Exploiting unlabelled photos for stronger fine-grained SBIR","author":"Sain","year":"2023"},{"issue":"4","key":"10.1016\/j.neunet.2026.109384_bib0042","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2897824.2925954","article-title":"The sketchy database: Learning to retrieve badly drawn bunnies","volume":"35","author":"Sangkloy","year":"2016","journal-title":"ACM Transactions on Graphics"},{"key":"10.1016\/j.neunet.2026.109384_bib0043","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3598","article-title":"Zero-shot sketch-image hashing","author":"Shen","year":"2018"},{"key":"10.1016\/j.neunet.2026.109384_bib0044","unstructured":"Song, J., Meng, C., & Ermon, S. (2020). Denoising diffusion implicit models. arXiv: 2010.02502."},{"key":"10.1016\/j.neunet.2026.109384_bib0045","series-title":"Proceedings of the international conference on artificial neural networks","first-page":"52","article-title":"Cross-modal attention alignment network with auxiliary text description for zero-shot sketch-based image retrieval","author":"Su","year":"2024"},{"key":"10.1016\/j.neunet.2026.109384_bib0046","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"8805","article-title":"Chain of visual perception: Harnessing multimodal large language models for zero-shot camouflaged object detection","author":"Tang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109384_bib0047","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F. et al. (2023). Llama: Open and efficient foundation language models. arXiv: 2302.13971."},{"key":"10.1016\/j.neunet.2026.109384_bib0048","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2017). Graph attention networks. arXiv: 1710.10903."},{"key":"10.1016\/j.neunet.2026.109384_bib0049","series-title":"Proceedings of the international joint conference on artificial intelligence","first-page":"1106","article-title":"Norm-guided adaptive visual embedding for zero-shot sketch-based image retrieval","author":"Wang","year":"2021"},{"issue":"11","key":"10.1016\/j.neunet.2026.109384_bib0050","doi-asserted-by":"crossref","first-page":"7024","DOI":"10.1109\/TCSVT.2023.3265697","article-title":"Cross-domain alignment for zero-shot sketch-based image retrieval","volume":"33","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109384_bib0051","unstructured":"Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021). Finetuned language models are zero-shot learners. arXiv: 2109.01652."},{"key":"10.1016\/j.neunet.2026.109384_bib0052","article-title":"LLM-LED vision-spectral fusion: A zero-shot approach to temporal fruit image classification","volume":"194","author":"Wu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109384_bib0053","article-title":"VLEXPan: A visual-enhanced llm framework with inductive and deductive policies for entity set expansion","volume":"195","author":"Wu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109384_bib0054","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5493","article-title":"Vit-comer: Vision transformer with convolutional multi-scale feature interaction for dense predictions","author":"Xia","year":"2024"},{"key":"10.1016\/j.neunet.2026.109384_bib0055","series-title":"Proceedings of the IEEE international conference on image processing","first-page":"3661","article-title":"Deep zero-shot learning for scene sketch","author":"Xie","year":"2019"},{"key":"10.1016\/j.neunet.2026.109384_bib0056","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"8978","article-title":"Zero-shot video moment retrieval via off-the-shelf multimodal large language models","volume":"vol. 39","author":"Xu","year":"2025"},{"key":"10.1016\/j.neunet.2026.109384_bib0057","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"1245","article-title":"Semantic editing increment benefits zero-shot composed image retrieval","author":"Yang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109384_bib0058","series-title":"Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval","first-page":"80","article-title":"LDRE: LLM-based divergent reasoning and ensemble for zero-shot composed image retrieval","author":"Yang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109384_bib0059","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"16504","article-title":"Asymmetric mutual alignment for unsupervised zero-shot sketch-based image retrieval","volume":"vol. 38","author":"Yin","year":"2024"},{"key":"10.1016\/j.neunet.2026.109384_bib0060","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"799","article-title":"Sketch me that shoe","author":"Yu","year":"2016"},{"key":"10.1016\/j.neunet.2026.109384_bib0061","article-title":"Enabling generalized zero-shot learning towards unseen domains by intrinsic learning from redundant LLM semantics","volume":"193","author":"Yue","year":"2025","journal-title":"Neural Networks"},{"issue":"12","key":"10.1016\/j.neunet.2026.109384_bib0062","doi-asserted-by":"crossref","first-page":"6309","DOI":"10.1007\/s00371-022-02731-8","article-title":"Stroke-based semantic segmentation for scene-level free-hand sketches","volume":"39","author":"Zhang","year":"2023","journal-title":"The Visual Computer"},{"key":"10.1016\/j.neunet.2026.109384_bib0063","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12943","article-title":"Zero-shot sketch-based image retrieval via graph convolution network","volume":"vol. 34","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109384_bib0064","series-title":"Proceedings of the international conference on machine learning","first-page":"42247","article-title":"Rleg: Vision-language representation learning with diffusion-based embedding generation","author":"Zhao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109384_bib0065","series-title":"Proceedings of the IEEE international conference on multimedia and expo","first-page":"1","article-title":"Ocean: A dual learning approach for generalized zero-shot sketch-based image retrieval","author":"Zhu","year":"2020"},{"issue":"10","key":"10.1016\/j.neunet.2026.109384_bib0066","doi-asserted-by":"crossref","first-page":"3096","DOI":"10.1109\/TNNLS.2018.2890018","article-title":"A deep collaborative framework for face photo\u2013sketch synthesis","volume":"30","author":"Zhu","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"2","key":"10.1016\/j.neunet.2026.109384_bib0067","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1109\/TNNLS.2020.3030536","article-title":"Knowledge distillation for face photo\u2013sketch synthesis","volume":"33","author":"Zhu","year":"2020","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"6","key":"10.1016\/j.neunet.2026.109384_bib0068","doi-asserted-by":"crossref","first-page":"1820","DOI":"10.1007\/s11263-021-01442-2","article-title":"Learning deep patch representation for probabilistic graphical model-based face sketch synthesis","volume":"129","author":"Zhu","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109384_bib0069","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2026.108586","article-title":"ADAAlign: A unified solution for traditional and modern zero-shot sketch-based image retrieval","volume":"198","author":"Zhu","year":"2026","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109384_bib0070","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020c). Deformable detr: Deformable transformers for end-to-end object detection. arXiv: 2010.04159."},{"key":"10.1016\/j.neunet.2026.109384_bib0071","series-title":"Proceedings of the european conference on computer vision","first-page":"421","article-title":"Sketchyscene: Richly-annotated scene sketches","author":"Zou","year":"2018"},{"key":"10.1016\/j.neunet.2026.109384_bib0072","series-title":"Proceedings of the international joint conference on artificial intelligence","article-title":"SceneDIFF: Generative scene-level image retrieval with text and sketch using diffusion models","author":"Zuo","year":"2024"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008427?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008427?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T20:06:39Z","timestamp":1790107599000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026008427"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":72,"alternative-id":["S0893608026008427"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109384","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FreeScene: Generative-enhanced visual modeling for generalized zero-shot image retrieval with scene sketches","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109384","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":"109384"}}