{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T06:36:17Z","timestamp":1770705377426,"version":"3.49.0"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732010","type":"print"},{"value":"9783031732027","type":"electronic"}],"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\/978-3-031-73202-7_11","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T14:17:45Z","timestamp":1732112265000},"page":"179-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Unveiling Typographic Deceptions: Insights of\u00a0the\u00a0Typographic Vulnerability in\u00a0Large Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Hao","family":"Cheng","sequence":"first","affiliation":[]},{"given":"Erjia","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Jindong","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Le","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jinhao","family":"Duan","sequence":"additional","affiliation":[]},{"given":"Jize","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jiahang","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Kaidi","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Renjing","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Acharya, M., Kafle, K., Kanan, C.: TallyQA: answering complex counting questions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 8076\u20138084 (2019)","DOI":"10.1609\/aaai.v33i01.33018076"},{"key":"11_CR2","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18208\u201318218 (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Azuma, H., Matsui, Y.: Defense-prefix for preventing typographic attacks on clip. In: ICCV Workshop on Adversarial Robustness In the Real World (2023)","DOI":"10.1109\/ICCVW60793.2023.00392"},{"key":"11_CR5","unstructured":"Chen, S., et al.: Red teaming GPT-4V: are GPT-4V safe against uni\/multi-modal jailbreak attacks? arXiv preprint arXiv:2404.03411 (2024)"},{"key":"11_CR6","unstructured":"Cheng, H., Cao, J., Xiao, E., Sun, M., Xu, R.: Gaining the sparse rewards by exploring binary lottery tickets in spiking neural network. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2024)"},{"key":"11_CR7","unstructured":"Cheng, H., et al.: RBFormer: improve adversarial robustness of transformer by robust bias. In: British Machine Vision Conference (BMVC) (2024)"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, H., et al.: More or less (MoL): defending against multiple perturbation attacks on deep neural networks through model ensemble and compression. In: 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), pp. 645\u2013655. IEEE (2022)","DOI":"10.1109\/WACVW54805.2022.00071"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Conde, M.V., Turgutlu, K.: CLIP-Art: contrastive pre-training for fine-grained art classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3956\u20133960 (2021)","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"11_CR10","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11_CR12","unstructured":"Driess, D., et\u00a0al.: PaLM-E: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Duan, J., et al.: Shifting attention to relevance: towards the uncertainty estimation of large language models. In: The 62nd Annual Meeting of the Association for Computational Linguistics (ACL) (2024)","DOI":"10.18653\/v1\/2024.acl-long.276"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Duan, J., Fan, Q., Cheng, H., Shi, X., Xu, K.: Improve video representation with temporal adversarial augmentation. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI) (2023)","DOI":"10.24963\/ijcai.2023\/79"},{"key":"11_CR15","unstructured":"Fu, C., et\u00a0al.: MME: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394 (2023)"},{"key":"11_CR16","unstructured":"Gao, K., et al.: Inducing high energy-latency of large vision-language models with verbose images. arXiv preprint arXiv:2401.11170 (2024)"},{"key":"11_CR17","unstructured":"Gao, K., et al.: Energy-latency manipulation of multi-modal large language models via verbose samples. arXiv preprint arXiv:2404.16557 (2024)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Gao, P., et al.: CLIP-Adapter: better vision-language models with feature adapters. Int. J. Comput. Vis. 1\u201315 (2023)","DOI":"10.1007\/s11263-023-01891-x"},{"key":"11_CR19","doi-asserted-by":"publisher","unstructured":"Goh, G., et al.: Multimodal neurons in artificial neural networks. Distill (2021). https:\/\/doi.org\/10.23915\/distill.00030, https:\/\/distill.pub\/2021\/multimodal-neurons","DOI":"10.23915\/distill.00030"},{"key":"11_CR20","unstructured":"Gong, Y., et al.: Figstep: jailbreaking large vision-language models via typographic visual prompts. arXiv preprint arXiv:2311.05608 (2023)"},{"key":"11_CR21","unstructured":"Gu, J.: Responsible generative AI: what to generate and what not. arXiv preprint arXiv:2404.05783 (2024)"},{"key":"11_CR22","unstructured":"Gu, J., et al.: A systematic survey of prompt engineering on vision-language foundation models. arXiv preprint arXiv:2307.12980 (2023)"},{"key":"11_CR23","doi-asserted-by":"publisher","unstructured":"Gu, J., Tresp, V., Qin, Y.: Are vision transformers robust to patch perturbations? In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13672, pp. 404\u2013421. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19775-8_24","DOI":"10.1007\/978-3-031-19775-8_24"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: From images to textual prompts: zero-shot visual question answering with frozen large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10867\u201310877 (2023)","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"11_CR25","unstructured":"Han, D., Jia, X., Bai, Y., Gu, J., Liu, Y., Cao, X.: Ot-attack: enhancing adversarial transferability of vision-language models via optimal transport optimization. arXiv preprint arXiv:2312.04403 (2023)"},{"key":"11_CR26","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Kong, F., et al.: Act-diffusion: efficient adversarial consistency training for one-step diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8890\u20138899 (2024)","DOI":"10.1109\/CVPR52733.2024.00849"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: Seed-bench: benchmarking multimodal llms with generative comprehension. arXiv preprint arXiv:2307.16125 (2023)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Li, D., Li, J., Le, H., Wang, G., Savarese, S., Hoi, S.C.: LAVIS: a one-stop library for language-vision intelligence. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pp. 31\u201341. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/aclanthology.org\/2023.acl-demo.3","DOI":"10.18653\/v1\/2023.acl-demo.3"},{"key":"11_CR30","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"11_CR31","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Li, L., Ma, R., Guo, Q., Xue, X., Qiu, X.: Bert-attack: adversarial attack against bert using bert. arXiv preprint arXiv:2004.09984 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"11_CR33","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":"11_CR34","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"11_CR35","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhu, Y., Gu, J., Lan, Y., Yang, C., Qiao, Y.: MM-SafetyBench: a benchmark for safety evaluation of multimodal large language models. arXiv preprint arXiv:2311.17600 (2023)","DOI":"10.1007\/978-3-031-72992-8_22"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Lu, D., Wang, Z., Wang, T., Guan, W., Gao, H., Zheng, F.: Set-level guidance attack: Boosting adversarial transferability of vision-language pre-training models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 102\u2013111 (2023)","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"11_CR38","unstructured":"Luo, H., Gu, J., Liu, F., Torr, P.: An image is worth 1000 lies: transferability of adversarial images across prompts on vision-language models. In: The Twelfth International Conference on Learning Representations"},{"key":"11_CR39","unstructured":"Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"11_CR40","unstructured":"Noever, D.A., Noever, S.E.M.: Reading isn\u2019t believing: adversarial attacks on multi-modal neurons. arXiv preprint arXiv:2103.10480 (2021)"},{"key":"11_CR41","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Paiss, R., et al.: Teaching clip to count to ten. arXiv preprint arXiv:2302.12066 (2023)","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"11_CR43","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR, 18\u201324 July 2021"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al.: DenseCLIP: language-guided dense prediction with context-aware prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18082\u201318091 (2022)","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"11_CR45","unstructured":"Rezaei, R., Sabet, M.J., Gu, J., Rueckert, D., Torr, P., Khakzar, A.: Learning visual prompts for guiding the attention of vision transformers. arXiv preprint arXiv:2406.03303 (2024)"},{"key":"11_CR46","unstructured":"Scao, T.L., et\u00a0al.: Bloom: a 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)"},{"key":"11_CR47","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. Adv. Neural Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"11_CR48","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"11_CR49","doi-asserted-by":"publisher","unstructured":"Schwenk, D., Khandelwal, A., Clark, C., Marino, K., Mottaghi, R.: A-OKVQA: a benchmark for visual question answering using world knowledge. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13668, pp. 146\u2013162. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20074-8_9","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"11_CR50","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"11_CR51","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"11_CR52","unstructured":"Wang, Z., et al.: Stop reasoning! When multimodal llms with chain-of-thought reasoning meets adversarial images. arXiv preprint arXiv:2402.14899 (2024)"},{"key":"11_CR53","unstructured":"Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., Duan, N.: Visual chatgpt: talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671 (2023)"},{"key":"11_CR54","doi-asserted-by":"crossref","unstructured":"Xu, P., et al.: Lvlm-ehub: a comprehensive evaluation benchmark for large vision-language models. arXiv preprint arXiv:2306.09265 (2023)","DOI":"10.1109\/TPAMI.2024.3507000"},{"key":"11_CR55","doi-asserted-by":"crossref","unstructured":"Yang, L., Han, Y., Chen, X., Song, S., Dai, J., Huang, G.: Resolution adaptive networks for efficient inference. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2369\u20132378 (2020)","DOI":"10.1109\/CVPR42600.2020.00244"},{"key":"11_CR56","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: CondenseNet V2: sparse feature reactivation for deep networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3569\u20133578 (2021)","DOI":"10.1109\/CVPR46437.2021.00357"},{"issue":"1","key":"11_CR57","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1109\/TCDS.2023.3274214","volume":"16","author":"L Yang","year":"2023","unstructured":"Yang, L., Zheng, Z., Wang, J., Song, S., Huang, G., Li, F.: AdaDet: an adaptive object detection system based on early-exit neural networks. IEEE Trans. Cogn. Dev. Syst. 16(1), 332\u2013345 (2023)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"11_CR58","unstructured":"Yin, S., et al.: A survey on multimodal large language models. arXiv preprint arXiv:2306.13549 (2023)"},{"key":"11_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yi, Q., Sang, J.: Towards adversarial attack on vision-language pre-training models. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5005\u20135013 (2022)","DOI":"10.1145\/3503161.3547801"},{"key":"11_CR60","doi-asserted-by":"publisher","unstructured":"Zhang, R., et al.: Tip-adapter: training-free adaption of CLIP for few-shot classification. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13695, pp. 493\u2013510. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_29","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"11_CR61","doi-asserted-by":"publisher","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from CLIP. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13688, pp. 696\u2013712. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_40","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"11_CR62","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"key":"11_CR63","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M., Fei-Fei, L.: Visual7w: grounded question answering in images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4995\u20135004 (2016)","DOI":"10.1109\/CVPR.2016.540"}],"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\/978-3-031-73202-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T16:54:21Z","timestamp":1733072061000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73202-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031732010","9783031732027"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73202-7_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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"}}]}}