{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:07:36Z","timestamp":1743142056620,"version":"3.40.3"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729034"},{"type":"electronic","value":"9783031729041"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-72904-1_2","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T13:27:07Z","timestamp":1732109227000},"page":"19-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Region-Native Visual Tokenization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3104-7725","authenticated-orcid":false,"given":"Mengyu","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8027-7523","authenticated-orcid":false,"given":"Yuyao","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4868-6526","authenticated-orcid":false,"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6974-7976","authenticated-orcid":false,"given":"Xinlong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Tiejun","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2812-8781","authenticated-orcid":false,"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8906-3777","authenticated-orcid":false,"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"2_CR2","unstructured":"Binkowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. In: ICLR. OpenReview.net (2018)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: CVPR, pp. 18392\u201318402. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"2_CR4","unstructured":"Burgess, C.P., et al.: MONet: unsupervised scene decomposition and representation. CoRR arXiv:1901.11390 (2019)"},{"key":"2_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"2_CR7","unstructured":"Cheng, B., Schwing, A.G., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) NeurIPS, pp. 17864\u201317875 (2021)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: CVPR, pp. 8789\u20138797. Computer Vision Foundation \/ IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00916"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Collins, E., Bala, R., Price, B., S\u00fcsstrunk, S.: Editing in style: uncovering the local semantics of GANs. In: CVPR, pp. 5770\u20135779. Computer Vision Foundation \/ IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.00581"},{"key":"2_CR10","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: DiffEdit: diffusion-based semantic image editing with mask guidance. In: ICLR. OpenReview.net (2023)"},{"key":"2_CR11","doi-asserted-by":"publisher","unstructured":"Crowson, K., et al.: VQGAN-CLIP: open domain image generation and editing with natural language guidance. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV, pp. 88\u2013105. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_6","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: CVPR, pp. 4690\u20134699. Computer Vision Foundation \/ IEEE (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"2_CR13","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) NAACL-HLT, pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., He, S., Jiang, X., Loy, C.C.: MeViS: a large-scale benchmark for video segmentation with motion expressions. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"2_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: ICLR. OpenReview.net (2021)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR, pp. 12873\u201312883. Computer Vision Foundation \/ IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Fernandez, P., Couairon, G., J\u00e9gou, H., Douze, M., Furon, T.: The stable signature: rooting watermarks in latent diffusion models. CoRR arXiv:2303.15435 (2023)","DOI":"10.1109\/ICCV51070.2023.02053"},{"key":"2_CR18","doi-asserted-by":"publisher","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.) ECCV, pp. 89\u2013106. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19784-0_6","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"2_CR19","unstructured":"Goel, V., et al.: Pair-diffusion: object-level image editing with structure-and-appearance paired diffusion models. CoRR arXiv:2303.17546 (2023)"},{"key":"2_CR20","unstructured":"Gondal, M.W., et al.: On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E.B., Garnett, R. (eds.) NeurIPS, pp. 15714\u201315725 (2019)"},{"key":"2_CR21","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) NeurIPS (2014)"},{"key":"2_CR22","unstructured":"H\u00e4rk\u00f6nen, E., Hertzmann, A., Lehtinen, J., Paris, S.: GANSpace: discovering interpretable GAN controls. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) NeurIPS (2020)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR24","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: Guyon, I., von Luxburg, U., Bengio, S., Wallach, H.M., Fergus, R., Vishwanathan, S.V.N., Garnett, R. (eds.) NeurIPS, pp. 6626\u20136637 (2017)"},{"key":"2_CR25","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) NeurIPS (2020)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Hor\u00e9, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: ICPR, pp. 2366\u20132369. IEEE Computer Society (2010)","DOI":"10.1109\/ICPR.2010.579"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Huang, M., Mao, Z., Chen, Z., Zhang, Y.: Towards accurate image coding: improved autoregressive image generation with dynamic vector quantization. In: CVPR, pp. 22596\u201322605 (2023)","DOI":"10.1109\/CVPR52729.2023.02164"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR, pp. 5967\u20135976. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"2_CR29","unstructured":"Kim, H., Mnih, A.: Disentangling by factorising. In: Dy, J.G., Krause, A. (eds.) ICML. Proceedings of Machine Learning Research, vol.\u00a080, pp. 2654\u20132663. PMLR (2018)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. CoRR arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Lee, C., Liu, Z., Wu, L., Luo, P.: MaskGAN: towards diverse and interactive facial image manipulation. In: CVPR, pp. 5548\u20135557. Computer Vision Foundation \/ IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"2_CR32","doi-asserted-by":"publisher","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., Han, W.: Autoregressive image generation using residual quantization. In: CVPR, pp. 11513\u201311522. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01123","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"2_CR33","doi-asserted-by":"publisher","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV, pp. 280\u2013296. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"2_CR34","unstructured":"Ling, H., Kreis, K., Li, D., Kim, S.W., Torralba, A., Fidler, S.: EditGAN: high-precision semantic image editing. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) NeurIPS, pp. 16331\u201316345 (2021)"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: GRES: generalized referring expression segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"issue":"1","key":"2_CR36","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/s44267-024-00049-8","volume":"2","author":"C Liu","year":"2024","unstructured":"Liu, C., Jiang, X., Ding, H.: PrimitiveNet: decomposing the global constraints for referring segmentation. Vis. Intell. 2(1), 16 (2024)","journal-title":"Vis. Intell."},{"key":"2_CR37","unstructured":"Locatello, F., et al.: Object-centric learning with slot attention. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) NeurIPS (2020)"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Ning, J., et al.: All in tokens: unifying output space of visual tasks via soft token. In: ICCV, pp. 19900\u201319910 (2023)","DOI":"10.1109\/ICCV51070.2023.01822"},{"key":"2_CR39","unstructured":"van\u00a0den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: Guyon, I., et al. (eds.) NeurIPS, pp. 6306\u20136315 (2017)"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Pan, X., Tewari, A., Leimk\u00fchler, T., Liu, L., Meka, A., Theobalt, C.: Drag your GAN: interactive point-based manipulation on the generative image manifold. In: Brunvand, E., Sheffer, A., Wimmer, M. (eds.) SIGGRAPH, pp. 78:1\u201378:11. ACM (2023)","DOI":"10.1145\/3588432.3591500"},{"key":"2_CR41","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"2_CR42","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"key":"2_CR43","unstructured":"Reed, S.E., Zhang, Y., Zhang, Y., Lee, H.: Deep visual analogy-making. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) NeurIPS, pp. 1252\u20131260 (2015)"},{"key":"2_CR44","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS, vol. 28 (2015)"},{"key":"2_CR45","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, pp. 10674\u201310685. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"4","key":"2_CR46","doi-asserted-by":"publisher","first-page":"2004","DOI":"10.1109\/TPAMI.2020.3034267","volume":"44","author":"Y Shen","year":"2022","unstructured":"Shen, Y., Yang, C., Tang, X., Zhou, B.: InterfaceGAN: interpreting the disentangled face representation learned by GANs. IEEE TPAMI 44(4), 2004\u20132018 (2022)","journal-title":"IEEE TPAMI"},{"key":"2_CR47","unstructured":"Shuai, X., Ding, H., Ma, X., Tu, R., Jiang, Y.G., Tao, D.: A survey of multimodal-guided image editing with text-to-image diffusion models. arXiv preprint arXiv:2406.14555 (2024)"},{"key":"2_CR48","unstructured":"Sohl-Dickstein, J., Weiss, E.A., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: Bach, F.R., Blei, D.M. (eds.) ICML. JMLR Workshop and Conference Proceedings, vol.\u00a037, pp. 2256\u20132265. JMLR.org (2015)"},{"issue":"4","key":"2_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459838","volume":"40","author":"O Tov","year":"2021","unstructured":"Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O., Cohen-Or, D.: Designing an encoder for styleGAN image manipulation. ACM TOG 40(4), 1\u201314 (2021)","journal-title":"ACM TOG"},{"key":"2_CR50","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) NeurIPS, pp. 5998\u20136008 (2017)"},{"key":"2_CR51","unstructured":"Wu, B., et al.: Visual transformers: token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677 (2020)"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Wu, R., Zhang, G., Lu, S., Chen, T.: Cascade EF-GAN: progressive facial expression editing with local focuses. In: CVPR, pp. 5020\u20135029. Computer Vision Foundation \/ IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.00507"},{"key":"2_CR53","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: GroupViT: semantic segmentation emerges from text supervision. In: CVPR, pp. 18113\u201318123. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"2_CR54","doi-asserted-by":"publisher","unstructured":"Yang, B., et al.: Paint by example: exemplar-based image editing with diffusion models. In: CVPR, pp. 18381\u201318391. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01763","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"2_CR55","doi-asserted-by":"crossref","unstructured":"Yang, T., Wang, Y., Lu, Y., Zheng, N.: Visual concepts tokenization. In: NeurIPS (2022)","DOI":"10.1515\/sem-2019-0107"},{"key":"2_CR56","unstructured":"Yu, J., et al.: Vector-quantized image modeling with improved VQGAN. In: ICLR. OpenReview.net (2022)"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: scene graph parsing with global context. In: CVPR, pp. 5831\u20135840 (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"2_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR, pp. 586\u2013595. Computer Vision Foundation \/ IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"2_CR59","doi-asserted-by":"publisher","unstructured":"Zhong, Y., Wang, L., Chen, J., Yu, D., Li, Y.: Comprehensive image captioning via scene graph decomposition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) ECCV, pp. 211\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_13","DOI":"10.1007\/978-3-030-58568-6_13"},{"key":"2_CR60","doi-asserted-by":"crossref","unstructured":"Zhu, J., Yang, C., Shen, Y., Shi, Z., Zhao, D., Chen, Q.: LinkGAN: linking GAN latents to pixels for controllable image synthesis. CoRR arXiv:2301.04604 (2023)","DOI":"10.1109\/ICCV51070.2023.00704"}],"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\/978-3-031-72904-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T19:52:02Z","timestamp":1742068322000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72904-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031729034","9783031729041"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72904-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 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"}}]}}