{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:37:17Z","timestamp":1757619437622,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819698653"},{"type":"electronic","value":"9789819698660"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-9866-0_24","type":"book-chapter","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T09:26:07Z","timestamp":1753262767000},"page":"275-286","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Remote Sensing Object Detection with LL-YOLO: Integrating Multi-modal Data Fusion and Latent Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7220-1539","authenticated-orcid":false,"given":"Qianchun","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5677-3077","authenticated-orcid":false,"given":"Zhuoxuan","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"24_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2019.111443","volume":"237","author":"N Levin","year":"2020","unstructured":"Levin, N., Kyba, C.C.M., Zhang, Q., et al.: Remote sensing of night lights: a review and an outlook for the future. Remote Sens. Environ. 237, 111443 (2020)","journal-title":"Remote Sens. Environ."},{"key":"24_CR2","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.isprsjprs.2016.03.014","volume":"117","author":"G Cheng","year":"2016","unstructured":"Cheng, G., Han, J.: A survey on object detection in optical remote sensing images. ISPRS J. Photogramm. Remote. Sens. 117, 11\u201328 (2016)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). IEEE. 1, pp. 886--893 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"24_CR4","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"24_CR5","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An Incremental Improvement. arXiv Preprint arXiv:1804.02767 (2018)"},{"key":"24_CR6","unstructured":"Radford, A., Kim, J. W., Hallacy, C., et al.: learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning. PMLR, pp. 8748--8763 (2021)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Huang, J., Wu, B., Duan, Q., et al.: A fast UAV trajectory planning framework in RIS-assisted communication systems with accelerated learning via multithreading and federating. IEEE Trans. Mob. Comput. (2025)","DOI":"10.1109\/TMC.2025.3544903"},{"key":"24_CR8","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: Proceedings of the International Conference on Machine Learning. PMLR, pp. 5583--5594 (2021)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Hou, X., Liu, M., Zhang, S., et al.: Salience DETR: enhancing detection transformer with hierarchical salience filtering refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17574--17583 (2024)","DOI":"10.1109\/CVPR52733.2024.01664"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Li, H., Chen, J., Zheng, A., et al.: Day-night cross-domain vehicle re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12626--12635 (2024)","DOI":"10.1109\/CVPR52733.2024.01200"},{"key":"24_CR11","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et al.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684--10695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Blattmann, A., Rombach, R., Ling, H., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563--22575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"24_CR14","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., et al.: Proximal Policy Optimization Algorithms. arXiv Preprint arXiv:1707.06347 (2017)"},{"issue":"9","key":"24_CR15","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"FA Croitoru","year":"2023","unstructured":"Croitoru, F.A., Hondru, V., Ionescu, R.T., et al.: Diffusion models in vision: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 10850\u201310869 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1\u20132","key":"24_CR16","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/S0010-0277(00)00157-8","volume":"80","author":"BJ Scholl","year":"2001","unstructured":"Scholl, B.J., Pylyshyn, Z.W., Feldman, J.: What is a visual object? evidence from target merging in multiple object tracking. Cognition 80(1\u20132), 159\u2013177 (2001)","journal-title":"Cognition"},{"key":"24_CR17","unstructured":"Liu, F., Tan, H., Tensmeyer, C.: DocumentCLIP: linking figures and main body text in reflowed documents. arXiv Preprint arXiv:2306.06306 (2023)"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Gao, S., Liu, X., Zeng, B., et al.: Implicit diffusion models for continuous super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10021--10030 (2023)","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"24_CR19","unstructured":"Pi, R., Zhang, J., Zhang, J., et al.: Image textualization: an automatic framework for creating accurate and detailed image descriptions. arXiv Preprint arXiv:2406.07502 (2024)"},{"key":"24_CR20","unstructured":"Devlin, J., Chang, M. W., Lee, K., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4171--4186 (2019)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Zheng, D., Dong, W., Hu, H., et al.: Less Is More: Focus Attention for Efficient DETR. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 6674--6683 (2023)","DOI":"10.1109\/ICCV51070.2023.00614"},{"issue":"3","key":"24_CR22","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/MSP.2003.1203207","volume":"20","author":"SC Park","year":"2003","unstructured":"Park, S.C., Park, M.K., Kang, M.G.: Super-resolution image reconstruction: a technical overview. IEEE Signal Process. Mag. 20(3), 21\u201336 (2003)","journal-title":"IEEE Signal Process. Mag."},{"key":"24_CR23","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1017\/jfm.2019.238","volume":"870","author":"K Fukami","year":"2019","unstructured":"Fukami, K., Fukagata, K., Taira, K.: Super-resolution reconstruction of turbulent flows with machine learning. J. Fluid Mech. 870, 106\u2013120 (2019)","journal-title":"J. Fluid Mech."},{"issue":"1","key":"24_CR24","doi-asserted-by":"publisher","first-page":"6350647","DOI":"10.1155\/2023\/6350647","volume":"2023","author":"B Wu","year":"2023","unstructured":"Wu, B., Wu, W.: Model-free cooperative optimal output regulation for linear discrete-time multi-agent systems using reinforcement learning. Math. Probl. Eng. 2023(1), 6350647 (2023)","journal-title":"Math. Probl. Eng."},{"key":"24_CR25","doi-asserted-by":"publisher","first-page":"81180","DOI":"10.1109\/ACCESS.2023.3299340","volume":"11","author":"B Wu","year":"2023","unstructured":"Wu, B., Cai, Z., Wu, W., et al.: AoI-aware resource management for smart health via deep reinforcement learning. IEEE Access. 11, 81180\u201381195 (2023)","journal-title":"IEEE Access."},{"key":"24_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-62015-7","volume-title":"Markov Chains","author":"KL Chung","year":"1967","unstructured":"Chung, K.L.: Markov Chains. Springer-Verlag, New York (1967)"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., et al.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510--4520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Cao, H., Wang, Y., Chen, J., et al.: Swin-Unet: unet-like pure transformer for medical image segmentation. In: European Conference on Computer Vision. Cham: Springer Nature Switzerland, pp. 205--218 (2022)","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, P., Li, X., Hu, X., et al.: VinVL: revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5579--5588 (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770--778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Nei, M., Maruyama, T., Chakraborty, R.: The Bottleneck Effect and Genetic Variability in Populations. Evolution. 1\u201310 (1975)","DOI":"10.1111\/j.1558-5646.1975.tb00807.x"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Cheng, T., Song, L., Ge, Y., et al.: Yolo-world: real-time open-vocabulary object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16901--16911 (2024)","DOI":"10.1109\/CVPR52733.2024.01599"},{"issue":"1","key":"24_CR33","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TCSVT.2023.3284161","volume":"34","author":"G Guo","year":"2023","unstructured":"Guo, G., Chen, P., Yu, X., et al.: Save the tiny, save the all: hierarchical activation network for tiny object detection. IEEE Trans. Circuits Syst. Video Technol. 34(1), 221\u2013234 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Ling, M., Chang, K., et al.: A two-stage enhancement method for object detection on low-resolution images. In: 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, pp. 1--8 (2024)","DOI":"10.1109\/IJCNN60899.2024.10650286"},{"key":"24_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3510781","volume":"62","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Ye, M., Zhu, G., et al.: FFCA-YOLO for small object detection in remote sensing images. IEEE Trans. Geosci. Remote Sens. 62, 1\u201315 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9866-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T19:43:10Z","timestamp":1757274190000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9866-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698653","9789819698660"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9866-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}