{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:12:35Z","timestamp":1780765955537,"version":"3.54.1"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731129","type":"print"},{"value":"9783031731136","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\/978-3-031-73113-6_5","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T08:53:56Z","timestamp":1732092836000},"page":"70-88","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":42,"title":["ProxyCLIP: Proxy Attention Improves CLIP for\u00a0Open-Vocabulary Segmentation"],"prefix":"10.1007","author":[{"given":"Mengcheng","family":"Lan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaofeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiping","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinjiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Litong","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wayne","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Barsellotti, L., Amoroso, R., Cornia, M., Baraldi, L., Cucchiara, R.: Training-free open-vocabulary segmentation with offline diffusion-augmented prototype generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3689\u20133698 (2024)","DOI":"10.1109\/CVPR52733.2024.00354"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Bousselham, W., Petersen, F., Ferrari, V., Kuehne, H.: Grounding everything: emerging localization properties in vision-language transformers. arXiv preprint arXiv:2312.00878 (2023)","DOI":"10.1109\/CVPR52733.2024.00367"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Cha, J., Mun, J., Roh, B.: Learning to generate text-grounded mask for open-world semantic segmentation from only image-text pairs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11165\u201311174 (2023)","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Zhu, D., et al.: Exploring open-vocabulary semantic segmentation from clip vision encoder distillation only. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 699\u2013710 (2023)","DOI":"10.1109\/ICCV51070.2023.00071"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"5_CR8","unstructured":"Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation. In: International Conference on Machine Learning, pp. 1931\u20131942. PMLR (2021)"},{"key":"5_CR9","unstructured":"MMSegmentation Contributors: MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark (2020)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"5_CR11","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers. arXiv preprint arXiv:2309.16588 (2023)"},{"key":"5_CR12","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"5_CR13","unstructured":"Everingham, M., Winn, J.: The PASCAL visual object classes challenge 2012 (VOC2012) development kit. Pattern Anal. Stat. Model. Comput. Learn. Tech. Rep 2007(1-45), 5 (2012)"},{"key":"5_CR14","unstructured":"Hamilton, M., Zhang, Z., Hariharan, B., Snavely, N., Freeman, W.T.: Unsupervised semantic segmentation by distilling feature correspondences. arXiv preprint arXiv:2203.08414 (2022)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"5_CR16","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":"5_CR17","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"5_CR18","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"5_CR19","unstructured":"Lan, M., Wang, X., Ke, Y., Xu, J., Feng, L., Zhang, W.: SmooSeg: smoothness prior for unsupervised semantic segmentation. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"5_CR20","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":"5_CR21","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR22","unstructured":"Li, Y., Wang, H., Duan, Y., Li, X.: Clip surgery for better explainability with enhancement in open-vocabulary tasks. arXiv preprint arXiv:2304.05653 (2023)"},{"key":"5_CR23","unstructured":"Li, Y., Li, Z., Zeng, Q., Hou, Q., Cheng, M.M.: Cascade-clip: cascaded vision-language embeddings alignment for zero-shot semantic segmentation. arXiv preprint arXiv:2406.00670 (2024)"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"5_CR25","unstructured":"Luo, H., Bao, J., Wu, Y., He, X., Li, T.: SegCLIP: patch aggregation with learnable centers for open-vocabulary semantic segmentation. In: International Conference on Machine Learning, pp. 23033\u201323044. PMLR (2023)"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 891\u2013898 (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Mukhoti, J., et al.: Open vocabulary semantic segmentation with patch aligned contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19413\u201319423 (2023)","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Naeem, M.F., Xian, Y., Zhai, X., Hoyer, L., Van\u00a0Gool, L., Tombari, F.: SILC: improving vision language pretraining with self-distillation. arXiv preprint arXiv:2310.13355 (2023)","DOI":"10.1007\/978-3-031-72664-4_3"},{"key":"5_CR29","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"5_CR31","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Rasheed, H., et al.: GLaMM: pixel grounding large multimodal model. arXiv preprint arXiv:2311.03356 (2023)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"5_CR33","unstructured":"Ren, P., et al.: ViewCo: discovering text-supervised segmentation masks via multi-view semantic consistency. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=2XLRBjY46O6"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"5_CR35","first-page":"33754","volume":"35","author":"G Shin","year":"2022","unstructured":"Shin, G., Xie, W., Albanie, S.: ReCo: retrieve and co-segment for zero-shot transfer. Adv. Neural. Inf. Process. Syst. 35, 33754\u201333767 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR36","unstructured":"Sim\u00e9oni, O., et al.: Localizing objects with self-supervised transformers and no labels. arXiv preprint arXiv:2109.14279 (2021)"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Sim\u00e9oni, O., Sekkat, C., Puy, G., Vobeck\u1ef3, A., Zablocki, \u00c9., P\u00e9rez, P.: Unsupervised object localization: Observing the background to discover objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3176\u20133186 (2023)","DOI":"10.1109\/CVPR52729.2023.00310"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Sun, S., Li, R., Torr, P., Gu, X., Li, S.: Clip as RNN: segment countless visual concepts without training endeavor. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13171\u201313182 (2024)","DOI":"10.1109\/CVPR52733.2024.01251"},{"key":"5_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Wang, F., Mei, J., Yuille, A.: SCLIP: rethinking self-attention for dense vision-language inference. arXiv preprint arXiv:2312.01597 (2023)","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"5_CR41","unstructured":"Wang, H., et al.: SAM-CLIP: merging vision foundation models towards semantic and spatial understanding. In: UniReps: The First Workshop on Unifying Representations in Neural Models (2023). https:\/\/openreview.net\/forum?id=md0mU6rN2u"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: FreeSOLO: learning to segment objects without annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14176\u201314186 (2022)","DOI":"10.1109\/CVPR52688.2022.01378"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Wang, X., Girdhar, R., Yu, S.X., Misra, I.: Cut and learn for unsupervised object detection and instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3124\u20133134 (2023)","DOI":"10.1109\/CVPR52729.2023.00305"},{"key":"5_CR44","doi-asserted-by":"publisher","first-page":"15790","DOI":"10.1109\/TPAMI.2023.3305122","volume":"45","author":"Y Wang","year":"2023","unstructured":"Wang, Y., et al.: TokenCut: segmenting objects in images and videos with self-supervised transformer and normalized cut. IEEE Trans. Pattern Anal. Mach. Intell. 45, 15790\u201315801 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, R., Luo, N., Pan, Y., Zhang, T.: Image-to-image matching via foundation models: a new perspective for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3952\u20133963 (2024)","DOI":"10.1109\/CVPR52733.2024.00379"},{"key":"5_CR46","unstructured":"Wu, S., et al.: CLIPSelf: vision transformer distills itself for open-vocabulary dense prediction. arXiv preprint arXiv:2310.01403 (2023)"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Wysocza\u0144ska, M., Ramamonjisoa, M., Trzci\u0144ski, T., Sim\u00e9oni, O.: CLIP-DIY: CLIP dense inference yields open-vocabulary semantic segmentation for-free. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1403\u20131413 (2024)","DOI":"10.1109\/WACV57701.2024.00143"},{"key":"5_CR48","unstructured":"Wysocza\u0144ska, M., Sim\u00e9oni, O., Ramamonjisoa, M., Bursuc, A., Trzci\u0144ski, T., P\u00e9rez, P.: CLIP-dinoiser: teaching CLIP a few DINO tricks. arXiv preprint arXiv:2312.12359 (2023)"},{"key":"5_CR49","unstructured":"Xing, Y., Kang, J., Xiao, A., Nie, J., Shao, L., Lu, S.: Rewrite caption semantics: bridging semantic gaps for language-supervised semantic segmentation. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=9iafshF7s3"},{"key":"5_CR50","unstructured":"Xu, H., et al.: Demystifying clip data. arXiv preprint arXiv:2309.16671 (2023)"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: GroupViT: semantic segmentation emerges from text supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Learning open-vocabulary semantic segmentation models from natural language supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2935\u20132944 (2023)","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"5_CR54","unstructured":"Yao, L., et al.: FILIP: fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783 (2021)"},{"key":"5_CR55","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/978-3-031-19818-2_5","volume-title":"ECCV 2022","author":"Z Yin","year":"2022","unstructured":"Yin, Z., et al.: TransFGU: a top-down approach to fine-grained unsupervised semantic segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13689, pp. 73\u201389. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_5"},{"key":"5_CR56","doi-asserted-by":"crossref","unstructured":"Yuan, H., Li, X., Zhou, C., Li, Y., Chen, K., Loy, C.C.: Open-vocabulary SAM: segment and recognize twenty-thousand classes interactively. arXiv preprint arXiv:2401.02955 (2024)","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"5_CR57","unstructured":"Yuan, L., et\u00a0al.: Florence: a new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)"},{"key":"5_CR58","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: LiT: zero-shot transfer with locked-image text tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"5_CR59","unstructured":"Zhang, F., et al.: Uncovering prototypical knowledge for weakly open-vocabulary semantic segmentation. arXiv preprint arXiv:2310.19001 (2023)"},{"key":"5_CR60","first-page":"36067","volume":"35","author":"H Zhang","year":"2022","unstructured":"Zhang, H., et al.: GLIPv2: unifying localization and vision-language understanding. Adv. Neural. Inf. Process. Syst. 35, 36067\u201336080 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR61","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: RegionCLIP: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"5_CR62","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ADE20K dataset. Int. J. Comput. Vision 127, 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"5_CR63","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-031-19815-1_40","volume-title":"ECCV 2022","author":"C Zhou","year":"2022","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.) ECCV 2022. LNCS, vol. 13688, pp. 696\u2013712. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_40"},{"key":"5_CR64","unstructured":"Zhou, J., et al.: iBOT: image BERT pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)"}],"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\/978-3-031-73113-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T16:17:30Z","timestamp":1733069850000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73113-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031731129","9783031731136"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73113-6_5","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"}}]}}