{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T18:52:21Z","timestamp":1774896741136,"version":"3.50.1"},"publisher-location":"Cham","reference-count":91,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729485","type":"print"},{"value":"9783031729492","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-72949-2_22","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:17Z","timestamp":1730301737000},"page":"381-399","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["BK-SDM: A Lightweight, Fast, and\u00a0Cheap Version of\u00a0Stable Diffusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0224-7985","authenticated-orcid":false,"given":"Bo-Kyeong","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6546-9593","authenticated-orcid":false,"given":"Hyoung-Kyu","family":"Song","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0549-5695","authenticated-orcid":false,"given":"Thibault","family":"Castells","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9617-2418","authenticated-orcid":false,"given":"Shinkook","family":"Choi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"22_CR1","unstructured":"A Simple and Effective Pruning Approach for LLMs. ICLR (2024)"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"22_CR5","unstructured":"Castells, T., et al.: EdgeFusion: on-device text-to-image generation. In: CVPR Workshop (2024)"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y.H., et al.: Speed is all you need: On-device acceleration of large diffusion models via GPU-aware optimizations. In: CVPR Workshop (2023)","DOI":"10.1109\/CVPRW59228.2023.00490"},{"key":"22_CR7","unstructured":"Choi, J., et al.: Squeezing large-scale diffusion models for mobile. In: ICML Workshop (2023)"},{"key":"22_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"22_CR9","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"22_CR10","unstructured":"Ding, M., et\u00a0al.: CogView: mastering text-to-image generation via transformers. In: NeurIPS (2021)"},{"key":"22_CR11","unstructured":"Ding, M., Zheng, W., Hong, W., Tang, J.: CogView2: faster and better text-to-image generation via hierarchical transformers. In: NeurIPS (2022)"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Fang, G., Ma, X., Song, M., Mi, M.B., Wang, X.: DepGraph: towards any structural pruning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"22_CR14","unstructured":"Fang, G., Ma, X., Wang, X.: Structural pruning for diffusion models. In: NeurIPS (2023)"},{"key":"22_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-031-19784-0_6","volume-title":"Computer Vision \u2013 ECCV 2022","author":"O Gafni","year":"2022","unstructured":"Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., Taigman, Y.: Make-a-scene: scene-based text-to-image generation with human priors. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. Lecture Notes in Computer Science, vol. 13675, pp. 89\u2013106. Springer, Cham (2022)"},{"key":"22_CR16","unstructured":"Hao, Z., et al.: Learning efficient vision transformers via fine-grained manifold distillation. In: NeurIPS (2022)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., Choi, J.Y.: A comprehensive overhaul of feature distillation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00201"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Le\u00a0Bras, R., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"22_CR20","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS (2017)"},{"key":"22_CR21","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NeurIPS Workshop (2014)"},{"key":"22_CR22","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"22_CR23","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS Workshop (2021)"},{"key":"22_CR24","unstructured":"Hou, J., Asghar, Z.: World\u2019s first on-device demonstration of stable diffusion on an android phone (2023). https:\/\/www.qualcomm.com\/news"},{"key":"22_CR25","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: ICML (2021)"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Jiao, X., et al.: TinyBERT: distilling BERT for natural language understanding. In: Findings of EMNLP (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up GANs for text-to-image synthesis. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"22_CR28","unstructured":"Kim, B.K., Choi, S., Park, H.: Cut inner layers: a structured pruning strategy for efficient U-net GANs. In: ICML Workshop (2022)"},{"key":"22_CR29","unstructured":"Kim, B.K., et al.: Shortened LLaMA: a simple depth pruning for large language models. arXiv preprint arXiv:2402.02834 (2024)"},{"key":"22_CR30","unstructured":"LeCun, Y., Denker, J., Solla, S.: Optimal brain damage. In: NeurIPS (1989)"},{"key":"22_CR31","unstructured":"Lee, Y., Park, K., Cho, Y., Lee, Y.J., Hwang, S.J.: KOALA: self-attention matters in knowledge distillation of latent diffusion models for memory-efficient and fast image synthesis. arXiv preprint arXiv:2312.04005v1 (2023)"},{"key":"22_CR32","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: ICLR (2017)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Li, M., Lin, J., Ding, Y., Liu, Z., Zhu, J.Y., Han, S.: GAN compression: efficient architectures for interactive conditional GANs. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00533"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Q-diffusion: quantizing diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"22_CR35","unstructured":"Li, Y., et al.: SnapFusion: text-to-image diffusion model on mobile devices within two seconds. In: NeurIPS (2023)"},{"key":"22_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"22_CR37","unstructured":"Liu, L., Ren, Y., Lin, Z., Zhao, Z.: Pseudo numerical methods for diffusion models on manifolds. In: ICLR (2022)"},{"key":"22_CR38","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. In: NeurIPS (2022)"},{"key":"22_CR39","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver++: fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)"},{"key":"22_CR40","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., Zhao, H.: Latent consistency models: synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378 (2023)"},{"key":"22_CR41","unstructured":"Mangrulkar, S., Gugger, S., Debut, L., Belkada, Y., Paul, S.: PEFT: state-of-the-art parameter-efficient fine-tuning methods (2022). https:\/\/github.com\/huggingface\/peft"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Meng, C., Gao, R., Kingma, D.P., Ermon, S., Ho, J., Salimans, T.: On distillation of guided diffusion models. In: NeurIPS Workshop (2022)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Meng, C., Gao, R., Kingma, D.P., Ermon, S., Ho, J., Salimans, T.: On distillation of guided diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"22_CR44","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: ICLR (2022)"},{"key":"22_CR45","unstructured":"Mo, S., Cho, M., Shin, J.: Freeze the discriminator: a simple baseline for fine-tuning GANs. In: CVPR Workshop (2020)"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Mallya, A., Tyree, S., Frosio, I., Kautz, J.: Importance estimation for neural network pruning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01152"},{"key":"22_CR47","unstructured":"Murti, C., Narshana, T., Bhattacharyya, C.: TVSPrune - pruning non-discriminative filters via total variation separability of intermediate representations without fine tuning. In: ICLR (2023)"},{"key":"22_CR48","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML (2022)"},{"key":"22_CR49","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., Cho, M.: Relational knowledge distillation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00409"},{"key":"22_CR50","unstructured":"Pernias, P., Rampas, D., Richter, M.L., Pal, C.J., Aubreville, M.: W\u00fcerstchen: an efficient architecture for large-scale text-to-image diffusion models. In: ICLR (2024)"},{"key":"22_CR51","unstructured":"Pinkney, J.: Small stable diffusion (2023). https:\/\/huggingface.co\/OFA-Sys\/small-stable-diffusion-v0"},{"key":"22_CR52","unstructured":"von Platen, P., et al.: Diffusers: state-of-the-art diffusion models (2022). https:\/\/github.com\/huggingface\/diffusers"},{"key":"22_CR53","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"22_CR54","unstructured":"Radford, A., et\u00a0al.: Language models are unsupervised multitask learners. OpenAI blog (2019)"},{"key":"22_CR55","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"22_CR56","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML (2021)"},{"key":"22_CR57","doi-asserted-by":"crossref","unstructured":"Ren, Y., Wu, J., Xiao, X., Yang, J.: Online multi-granularity distillation for GAN compression. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00672"},{"key":"22_CR58","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR59","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: LDM on celeba-hq (2022). https:\/\/huggingface.co\/CompVis\/ldm-celebahq-256"},{"key":"22_CR60","unstructured":"Rombach, R., Esser, P.: Stable diffusion v1-4 (2022). https:\/\/huggingface.co\/CompVis\/stable-diffusion-v1-4"},{"key":"22_CR61","unstructured":"Rombach, R., Esser, P.: Stable diffusion v1-5 (2022). https:\/\/huggingface.co\/runwayml\/stable-diffusion-v1-5"},{"key":"22_CR62","unstructured":"Rombach, R., Esser, P., Ha, D.: Stable diffusion v2-1-base (2022). https:\/\/huggingface.co\/stabilityai\/stable-diffusion-2-1-base"},{"key":"22_CR63","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. In: ICLR (2015)"},{"key":"22_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"22_CR65","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"22_CR66","doi-asserted-by":"crossref","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"22_CR67","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NeurIPS (2016)"},{"key":"22_CR68","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: ICLR (2022)"},{"key":"22_CR69","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. In: NeurIPS Workshop (2019)"},{"key":"22_CR70","unstructured":"Schuhmann, C., Beaumont, R.: LAION-aesthetics (2022). https:\/\/laion.ai\/blog\/laion-aesthetics"},{"key":"22_CR71","unstructured":"Schuhmann, C., et\u00a0al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: NeurIPS Workshop (2022)"},{"key":"22_CR72","unstructured":"Segmind: Segmind-distill-sd (2023). https:\/\/github.com\/segmind\/distill-sd\/tree\/c1e97a70d141df09e6fe5cc7dbd66e0cbeae3eeb"},{"key":"22_CR73","unstructured":"Segmind: SSD-1B (2023). https:\/\/github.com\/segmind\/SSD-1B\/tree\/d2ff723ea8ecf5dbd86f3aac0af1db30e88a2e2d"},{"key":"22_CR74","unstructured":"Shen, H., Cheng, P., Ye, X., Cheng, W., Abidi, H.: Accelerate stable diffusion with intel neural compressor (2022). https:\/\/medium.com\/intel-analytics-software"},{"key":"22_CR75","doi-asserted-by":"crossref","unstructured":"Shu, C., Liu, Y., Gao, J., Yan, Z., Shen, C.: Channel-wise knowledge distillation for dense prediction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"22_CR76","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"22_CR77","doi-asserted-by":"crossref","unstructured":"Sun, Z., Yu, H., Song, X., Liu, R., Yang, Y., Zhou, D.: MobileBERT: a compact task-agnostic BERT for resource-limited devices. In: ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"22_CR78","doi-asserted-by":"crossref","unstructured":"Tang, R., et al.: What the DAAM: interpreting stable diffusion using cross attention. In: ACL (2023)","DOI":"10.18653\/v1\/2023.acl-long.310"},{"key":"22_CR79","doi-asserted-by":"crossref","unstructured":"Tao, M., Bao, B.K., Tang, H., Xu, C.: GALIP: generative adversarial clips for text-to-image synthesis. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"22_CR80","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers and distillation through attention. In: ICML (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"22_CR81","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. In: NeurIPS (2017)"},{"key":"22_CR82","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"22_CR83","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score Jacobian chaining: lifting pretrained 2D diffusion models for 3D generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"22_CR84","doi-asserted-by":"crossref","unstructured":"Yu, L., Xiang, W.: X-pruner: explainable pruning for vision transformers. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02333"},{"key":"22_CR85","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: ICLR (2017)"},{"key":"22_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, L., Chen, X., Tu, X., Wan, P., Xu, N., Ma, K.: Wavelet knowledge distillation: towards efficient image-to-image translation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01214"},{"key":"22_CR87","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"22_CR88","unstructured":"Zhang, Q., Chen, Y.: Fast sampling of diffusion models with exponential integrator. In: ICLR (2023)"},{"key":"22_CR89","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xu, Y., Xiao, Z., Hou, T.: MobileDiffusion: Subsecond text-to-image generation on mobile devices. arXiv preprint arXiv:2311.16567 (2023)","DOI":"10.1007\/978-3-031-73033-7_13"},{"key":"22_CR90","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: Towards language-free training for text-to-image generation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"22_CR91","unstructured":"Zhu, L.: Thop: Pytorch-opcounter (2018). https:\/\/github.com\/Lyken17\/pytorch-OpCounter"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72949-2_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T14:26:08Z","timestamp":1732976768000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72949-2_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031729485","9783031729492"],"references-count":91,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72949-2_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}