{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T03:25:00Z","timestamp":1787369100053,"version":"build-2736575974"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000005","name":"U.S. Department of Defense","doi-asserted-by":"publisher","award":["W911NF-241-0295"],"award-info":[{"award-number":["W911NF-241-0295"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s11263-026-02947-4","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T08:29:25Z","timestamp":1784795365000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Diversifying Similar Subjects for Text-to-Image Synthesis with Self-Cross Diffusion Guidance and Reward"],"prefix":"10.1007","volume":"134","author":[{"given":"Weimin","family":"Qiu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieke","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhining","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent Tao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2984-1343","authenticated-orcid":false,"given":"Meng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"key":"2947_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., & Anadkat, S. (2023). Gpt-4 technical report. arXiv preprint arXiv:2303.08774."},{"key":"2947_CR2","doi-asserted-by":"crossref","unstructured":"Agarwal, A., Karanam, S., Joseph, K. J., Saxena, A., Goswami, K., & Srinivasan, B. V. (2023). A-star: Test-time attention segregation and retention for text-to-image synthesis. In ICCV (pp. 2283\u20132293).","DOI":"10.1109\/ICCV51070.2023.00217"},{"key":"2947_CR3","unstructured":"Aliasghar, K., Saeid, T., Asgari, A., Ali, S., Mahdavi, A., & Ghassan, H. (2024). Slime: Segment like me. In ICLR."},{"key":"2947_CR4","doi-asserted-by":"crossref","unstructured":"Bao, Z., Li, Y., Singh, K. K., Wang, Y.-X., & Hebert, M. (2024). Separate-and-enhance: Compositional finetuning for text2image diffusion models. In SIGGRAPH.","DOI":"10.1145\/3641519.3657527"},{"issue":"3","key":"2947_CR5","first-page":"8","volume":"2","author":"J Betker","year":"2023","unstructured":"Betker, J., Goh, G., Jing, L., Brooks, T., Wang, J., Li, L., Ouyang, L., Zhuang, J., Lee, J., Guo, Y., et al. (2023). Improving image generation with better captions. Computer Science., 2(3), 8. https:\/\/cdnopenai.com\/papers\/dall-e-3.pdf.","journal-title":"Computer Science."},{"key":"2947_CR6","doi-asserted-by":"crossref","unstructured":"Binyamin, L., Tewel, Y., Segev, H., Hirsch, E., Rassin, R., & Chechik, G. (2024). Make it count: Text-to-image generation with an accurate number of objects. arXiv preprint arXiv:2406.10210.","DOI":"10.1109\/CVPR52734.2025.01236"},{"key":"2947_CR7","unstructured":"Brooks, T., Peebles, B., Holmes, C., DePue, W., Guo, Y., Jing, L., Schnurr, D., Taylor, J., Luhman, T., Luhman, E., Ng, C., Wang, R., & Ramesh, A. (2024). Video generation models as world simulators. https:\/\/openai.com\/research\/video-generation-models-as-world-simulators."},{"key":"2947_CR8","doi-asserted-by":"crossref","unstructured":"Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., & Zheng, Y. (2023). Masactrl: Tuning-free mutual self-attention control for consistent image synthesis and editing. In ICCV (pp. 22560\u201322570).","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"2947_CR9","unstructured":"Chang, H., Zhang, H., Barber, J., Maschinot, A., Lezama, J., Jiang, L., Yang, M.-H., Murphy, K. P., Freeman, W. T., Rubinstein, M., Li, Y., & Krishnan, D. (2023). Muse: Text-to-image generation via masked generative transformers. In ICML."},{"issue":"4","key":"2947_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., & Cohen-Or, D. (2023). Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. ACM Transactions on Graphics (TOG), 42(4), 1\u201310.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2947_CR11","unstructured":"Dhariwal, P., N., & A. (2021). Diffusion models beat gans on image synthesis. NeurIPS."},{"key":"2947_CR12","first-page":"19822","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M., Yang, Z., Hong, W., Zheng, W., Zhou, C., Yin, D., Lin, J., Zou, X., Shao, Z., Yang, H., et al. (2021). Cogview: Mastering text-to-image generation via transformers. NeurIPS, 34, 19822\u201319835.","journal-title":"NeurIPS"},{"key":"2947_CR13","first-page":"16890","volume":"35","author":"M Ding","year":"2022","unstructured":"Ding, M., Zheng, W., Hong, W., & Tang, J. (2022). Cogview2: Faster and better text-to-image generation via hierarchical transformers. NeurIPS, 35, 16890\u201316902.","journal-title":"NeurIPS"},{"key":"2947_CR14","first-page":"16222","volume":"36","author":"D Epstein","year":"2023","unstructured":"Epstein, D., Jabri, A., Poole, B., Efros, A., & Holynski, A. (2023). Diffusion self-guidance for controllable image generation. NeurIPS, 36, 16222\u201316239.","journal-title":"NeurIPS"},{"key":"2947_CR15","unstructured":"Esser, P., Kulal, S., Blattmann, A., Entezari, R., M\u00fcller, J., Saini, H., Levi, Y., Lorenz, D., Sauer, A., & Boesel, F. (2024). Scaling rectified flow transformers for high-resolution image synthesis. In ICML."},{"key":"2947_CR16","doi-asserted-by":"crossref","unstructured":"Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., & Taigman, Y. (2022). Make-a-scene: Scene-based text-to-image generation with human priors. In ECCV (pp. 89\u2013106). Springer.","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"2947_CR17","doi-asserted-by":"crossref","unstructured":"Ge, S., Park, T., Zhu, J.-Y., & Huang, J.-B. (2023). Expressive text-to-image generation with rich text. In ICCV (pp. 7545\u20137556).","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"2947_CR18","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. NeurIPS, 27."},{"key":"2947_CR19","doi-asserted-by":"crossref","unstructured":"Guo, X., Liu, J., Cui, M., Li, J., Yang, H., & Huang, D. (2024). Initno: Boosting text-to-image diffusion models via initial noise optimization. In CVPR.","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"2947_CR20","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., & Cohen-or, D. (2023). Prompt-to-prompt image editing with cross-attention control. In ICLR. https:\/\/openreview.net\/forum?id=_CDixzkzeyb."},{"key":"2947_CR21","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., & Cohen-Or, D. (2022). Prompt-to-prompt image editing with cross attention control."},{"key":"2947_CR22","unstructured":"Ho, J. (2022). Classifier-free diffusion guidance arXiv:2207.12598."},{"key":"2947_CR23","first-page":"6840","volume-title":"NeurIPS","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, & H. Lin (Eds.), NeurIPS (Vol. 33, pp. 6840\u20136851). New York: Curran Associates Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf."},{"key":"2947_CR24","doi-asserted-by":"crossref","unstructured":"Hu, Y., Liu, B., Kasai, J., Wang, Y., Ostendorf, M., Krishna, R., & Smith, N. A. (2023). Tifa: Accurate and interpretable text-to-image faithfulness evaluation with question answering. In ICCV (pp. 20406\u201320417).","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"2947_CR25","doi-asserted-by":"publisher","unstructured":"Huang, K., Duan, C., Sun, K., Xie, E., Li, Z., & Liu, X. T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-Image Generation. TPAMI, (01), 1\u201317. January 5555. ISSN 1939-3539. https:\/\/doi.org\/10.1109\/TPAMI.2025.3531907.","DOI":"10.1109\/TPAMI.2025.3531907"},{"key":"2947_CR26","doi-asserted-by":"crossref","unstructured":"Huang, K., Sun, K., Xie, E., Li, Z., & Liu, X. (2023). T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation. arXiv preprint arXiv: 2307.06350.","DOI":"10.52202\/075280-3443"},{"key":"2947_CR27","doi-asserted-by":"crossref","unstructured":"Kang, M., Zhu, J.-Y., Zhang, R., Park, J., Shechtman, E., Paris, S., & Park, T. (2023). Scaling up gans for text-to-image synthesis. In CVPR (pp. 10124\u201310134).","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"2947_CR28","doi-asserted-by":"crossref","unstructured":"Karmann, M., & Urfalioglu, O. (2025). Repurposing stable diffusion attention for training-free unsupervised interactive segmentation. In CVPR.","DOI":"10.1109\/CVPR52734.2025.02283"},{"key":"2947_CR29","doi-asserted-by":"crossref","unstructured":"Kawano, Y., & Aoki, Y. (2024). Maskdiffusion: Exploiting pre-trained diffusion models for semantic segmentation.","DOI":"10.1109\/ACCESS.2024.3456442"},{"key":"2947_CR30","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, J., Kim, J.-H., Ha, J.-W., & Zhu, J.-Y. (2023). Dense text-to-image generation with attention modulation. In ICCV (pp. 7701\u20137711).","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"2947_CR31","doi-asserted-by":"crossref","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., & Han, W.-S. (2022). Autoregressive image generation using residual quantization. In CVPR (pp. 11523\u201311532).","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"2947_CR32","unstructured":"Li, J., Li, D., Xiong, C., & Hoi, S. (2022). Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In ICML."},{"key":"2947_CR33","unstructured":"Liu, L., Ren, Y., Lin, Z., & Zhao, Z. (2022). Pseudo numerical methods for diffusion models on manifolds. In ICLR. https:\/\/openreview.net\/forum?id=PlKWVd2yBkY."},{"key":"2947_CR34","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, G., Liang, J., Li, Y., Liu, J., Wang, X., Wan, P., Zhang, D., & Ouyang, W. (2025). Flow-grpo: Training flow matching models via online rl. NeurIPS.","DOI":"10.52202\/085713-1362"},{"key":"2947_CR35","unstructured":"Meng, C., He, Y., Song, Y., Song, J., Wu, J., Zhu, J.-Y., & Ermon, S. (2021). Sdedit: Guided image synthesis and editing with stochastic differential equations. In ICLR."},{"key":"2947_CR36","doi-asserted-by":"crossref","unstructured":"Meral, T. H. S., Simsar, E., Tombari, F., Y., & P. (2024). Conform: Contrast is all you need for high-fidelity text-to-image diffusion models. In CVPR (pp. 9005\u20139014).","DOI":"10.1109\/CVPR52733.2024.00860"},{"key":"2947_CR37","doi-asserted-by":"crossref","unstructured":"Mo, S., Mu, F., Lin, K. H., Liu, Y., Guan, B., Li, Y., & Zhou, B. (2024). Freecontrol: Training-free spatial control of any text-to-image diffusion model with any condition. In CVPR (pp. 7465\u20137475).","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"2947_CR38","unstructured":"Nichol, A.\u00a0Q. & Dhariwal, P. (2021). Improved denoising diffusion probabilistic models. In Proceedings of Machine Learning Research (Vol. 139, pp. 8162\u20138171). PMLR. https:\/\/proceedings.mlr.press\/v139\/nichol21a.html."},{"key":"2947_CR39","doi-asserted-by":"crossref","unstructured":"Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics: Systems.","DOI":"10.1109\/TSMC.1979.4310076"},{"key":"2947_CR40","unstructured":"Peter, R., & J. (1987). Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics."},{"key":"2947_CR41","doi-asserted-by":"crossref","unstructured":"Phung, Q., Ge, S., & Huang, J.-B. (2024). Grounded text-to-image synthesis with attention refocusing. In CVPR (pp. 7932\u20137942).","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"2947_CR42","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., & Rombach, R. (2024). SDXL: Improving latent diffusion models for high-resolution image synthesis. In ICLR. https:\/\/openreview.net\/forum?id=di52zR8xgf."},{"key":"2947_CR43","unstructured":"Poole, B., Jain, A., Barron, J. T., & Mildenhall, B. (2023). Dreamfusion: Text-to-3d using 2d diffusion. In ICLR."},{"key":"2947_CR44","doi-asserted-by":"crossref","unstructured":"Qiu, W., Wang, J., & Tang, M. (2025). Self-cross diffusion guidance for text-to-image synthesis of similar subjects. In CVPR.","DOI":"10.1109\/CVPR52734.2025.02191"},{"key":"2947_CR45","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., C., & M. (2022). Hierarchical text-conditional image generation with clip latents. In arxiv."},{"key":"2947_CR46","unstructured":"Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021). Zero-shot text-to-image generation. In ICML (pp. 8821\u20138831). PMLR."},{"key":"2947_CR47","doi-asserted-by":"crossref","unstructured":"Rassin, R., Hirsch, E., Glickman, D., Ravfogel, S., Goldberg, Y., & Chechik, G. (2024). Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment. NeurIPS, 36.","DOI":"10.52202\/075280-0157"},{"key":"2947_CR48","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2947_CR49","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In MICCAI.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2947_CR50","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E. L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al. (2022). Photorealistic text-to-image diffusion models with deep language understanding. NeurIPS, 35, 36479\u201336494.","journal-title":"NeurIPS"},{"key":"2947_CR51","unstructured":"Sauer, A., Karras, T., Laine, S., Geiger, A., A., & T. (2023). Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis. In ICML (pp. 30105\u201330118). PMLR."},{"key":"2947_CR52","unstructured":"Segalis, E., Valevski, D., Lumen, D., Matias, Y., & Leviathan, Y. (2023). A picture is worth a thousand words: Principled recaptioning improves image generation. arXiv:2310.16656."},{"key":"2947_CR53","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., & Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of Machine Learning Research (Vol. 37, pp. 2256\u20132265). Lille, France. PMLR. https:\/\/proceedings.mlr.press\/v37\/sohl-dickstein15.html."},{"key":"2947_CR54","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2021). Score-based generative modeling through stochastic differential equations. In ICLR."},{"key":"2947_CR55","doi-asserted-by":"crossref","unstructured":"Tao, M., Tang, H., Wu, F., Jing, X.-Y., Bao, B.-K., & Xu, C. (2022). Df-gan: A simple and effective baseline for text-to-image synthesis. In CVPR (pp. 16515\u201316525).","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"2947_CR56","unstructured":"Tianyi, W., Dongdong, C., Yifan, Z., & Xingang, P. (2024). Enhancing mmdit-based text-to-image models for similar subject generation. arXiv:2411.18301."},{"key":"2947_CR57","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., & Dekel, T. (2023). Plug-and-play diffusion features for text-driven image-to-image translation. In CVPR (pp. 1921\u20131930).","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"2947_CR58","volume-title":"NeurIPS","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141, & Polosukhin, I. (2017). Attention is all you need. In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), NeurIPS.  (Vol. 30). New York: Curran Associates Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf."},{"key":"2947_CR59","doi-asserted-by":"crossref","unstructured":"Wang, Z., Sha, Z., Ding, Z., Wang, Y., & Tu, Z. (2024) Tokencompose: Text-to-image diffusion with token-level supervision. In CVPR (pp. 8553\u20138564).","DOI":"10.1109\/CVPR52733.2024.00817"},{"key":"2947_CR60","unstructured":"Xiaofei, H., Qian, W., Hossein, R., J., & L. (2024). Class-agnostic object counting with text-to-image diffusion model. In ECCV."},{"key":"2947_CR61","doi-asserted-by":"crossref","unstructured":"Xie, J., Li, Y., Huang, Y., Liu, H., Zhang, W., Zheng, Y., & Shou, M.\u00a0Z. (2023). Boxdiff: Text-to-image synthesis with training-free box-constrained diffusion. In ICCV (pp. 7452\u20137461).","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"2947_CR62","doi-asserted-by":"crossref","unstructured":"Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang, X., & He, X. (2018). Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In CVPR (pp. 1316\u20131324).","DOI":"10.1109\/CVPR.2018.00143"},{"key":"2947_CR63","unstructured":"Yu, L., Shi, B., Pasunuru, R., Muller, B., Golovneva, O., Wang, T., Babu, A., Tang, B., Karrer, B., Sheynin, S., et\u00a0al. (2023). Scaling autoregressive multi-modal models: Pretraining and instruction tuning, 2(3). arXiv preprint arXiv:2309.02591."},{"key":"2947_CR64","unstructured":"Yu, J., Xu, Y., Koh, J.\u00a0Y., Luong, T., Baid, G., Wang, Z., Vasudevan, V., Ku, A., Yang, Y., Ayan, B.\u00a0K., Hutchinson, B., Han, W., Parekh, Z., Li, X., Zhang, H., Baldridge, J., & Wu, Y. (2022). Scaling autoregressive models for content-rich text-to-image generation. In TMLR. ISSN 2835-8856. Featured Certification."},{"key":"2947_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yang, M., Zhou, Q., W., & Z. (2024). Attention calibration for disentangled text-to-image personalization. In CVPR (pp. 4764\u20134774).","DOI":"10.1109\/CVPR52733.2024.00456"},{"key":"2947_CR66","doi-asserted-by":"crossref","unstructured":"Zheng, W., Teng, J., Yang, Z., Wang, W., Chen, J., Gu, X., Dong, Y., Ding, M., & Tang, J. (2024). Cogview3: Finer and faster text-to-image generation via relay diffusion. arXiv preprint arXiv:2403.05121.","DOI":"10.1007\/978-3-031-72980-5_1"},{"key":"2947_CR67","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., Y., & Y. (2019). Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis. In CVPR (pp. 5802\u20135810).","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02947-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02947-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02947-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T03:22:10Z","timestamp":1787368930000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02947-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,23]]},"references-count":67,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["2947"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02947-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,23]]},"assertion":[{"value":"19 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"359"}}