{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T16:22:18Z","timestamp":1786724538261,"version":"3.56.0"},"publisher-location":"Cham","reference-count":76,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726637","type":"print"},{"value":"9783031726644","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72664-4_18","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:04Z","timestamp":1729875724000},"page":"315-332","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":78,"title":["SCLIP: Rethinking Self-Attention for\u00a0Dense Vision-Language Inference"],"prefix":"10.1007","author":[{"given":"Feng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieru","family":"Mei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Araslanov, N., Roth, S.: Single-stage semantic segmentation from image labels. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00431"},{"key":"18_CR2","unstructured":"Bao, H., Dong, L., Wei, F.: BEiT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"18_CR3","unstructured":"Bommasani, R., et al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"18_CR4","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: COCO-stuff: thing and stuff classes in context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"18_CR7","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":"18_CR8","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"18_CR9","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"18_CR10","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 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"18_CR11","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: NeurIPS (2021)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"18_CR13","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: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR14","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"18_CR15","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: CSWin transformer: a general vision transformer backbone with cross-shaped windows. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"18_CR17","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Everingham, M., Eslami, S.A., Van\u00a0Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The Pascal visual object classes challenge: a retrospective. IJCV 111, 98\u2013136 (2015)","DOI":"10.1007\/s11263-014-0733-5"},{"key":"18_CR19","unstructured":"Gao, P., et al.: Clip-adapter: better vision-language models with feature adapters. arXiv preprint arXiv:2110.04544 (2021)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Gu, X., Cui, Y., Lin, T.Y.: Scaling open-vocabulary image segmentation with image-level labels. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"18_CR21","unstructured":"Grill, J.B., et al.: Bootstrap your own latent a new approach to self-supervised learning. In: NeurIPS (2020)"},{"key":"18_CR22","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"18_CR23","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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"18_CR25","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":"18_CR26","doi-asserted-by":"crossref","unstructured":"H\u00e9naff, O.J., Koppula, S., Alayrac, J.B., Van\u00a0den Oord, A., Vinyals, O., Carreira, J.: Efficient visual pretraining with contrastive detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10086\u201310096 (2021)","DOI":"10.1109\/ICCV48922.2021.00993"},{"key":"18_CR27","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":"18_CR28","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Karazija, L., Laina, I., Vedaldi, A., Rupprecht, C.: Diffusion models for zero-shot open-vocabulary segmentation. arXiv preprint arXiv:2306.09316 (2023)","DOI":"10.1007\/978-3-031-72652-1_18"},{"key":"18_CR30","unstructured":"Kirillov, A., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"18_CR31","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: NeurIPS (2011)"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: ACSeg: adaptive conceptualization for unsupervised semantic segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00692"},{"key":"18_CR33","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":"18_CR34","unstructured":"Liang, P.P., Zadeh, A., Morency, L.P.: Foundations and recent trends in multimodal machine learning: principles, challenges, and open questions. arXiv preprint arXiv:2209.03430 (2022)"},{"key":"18_CR35","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Q., Wen, Y., Han, J., Xu, C., Xu, H., Liang, X.: Open-world semantic segmentation via contrasting and clustering vision-language embedding. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20044-1_16"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer V2: scaling up capacity and resolution. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"18_CR39","unstructured":"Luo, H., Bao, J., Wu, Y., He, X., Li, T.: SegCLIP: patch aggregation with learnable centers for open-vocabulary semantic segmentation. In: ICML (2023)"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Mukhoti, J., et al.: Open vocabulary semantic segmentation with patch aligned contrastive learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"18_CR42","unstructured":"Nichol, A.Q., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML (2022)"},{"key":"18_CR43","unstructured":"Pham, H., et al.: Combined scaling for open-vocabulary image classification. arXiv preprint arXiv:2111.10050 (2021)"},{"key":"18_CR44","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"18_CR45","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR 21(140), 1\u201367 (2020)"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Ranasinghe, K., McKinzie, B., Ravi, S., Yang, Y., Toshev, A., Shlens, J.: Perceptual grouping in contrastive vision-language models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"18_CR47","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":"18_CR48","unstructured":"Shen, S., et al.: How much can clip benefit vision-and-language tasks? arXiv preprint arXiv:2107.06383 (2021)"},{"key":"18_CR49","unstructured":"Shin, G., Xie, W., Albanie, S.: ReCo: retrieve and co-segment for zero-shot transfer. In: NeurIPS (2022)"},{"key":"18_CR50","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"18_CR51","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Tu, Z., et al.: MaxVIT: multi-axis vision transformer. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"18_CR53","unstructured":"Wang, F., Li, M., Lin, X., Lv, H., Schwing, A.G., Ji, H.: Learning to decompose visual features with latent textual prompts. arXiv preprint arXiv:2210.04287 (2022)"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Wang, F., Wang, H., Wei, C., Yuille, A., Shen, W.: CP2: copy-paste contrastive pretraining for semantic segmentation. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20056-4_29"},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhu, Y., Adam, H., Yuille, A., Chen, L.C.: MaX-DeepLab: end-to-end panoptic segmentation with mask transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., Chen, L.C.: Axial-DeepLab: stand-alone axial-attention for panoptic segmentation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"18_CR57","unstructured":"Wang, W., et al.: CrossFormer++: a versatile vision transformer hinging on cross-scale attention. arXiv preprint arXiv:2303.06908 (2023)"},{"key":"18_CR58","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.Y., Yuille, A., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"18_CR59","unstructured":"Wu, S., et al.: CLIPSelf: vision transformer distills itself for open-vocabulary dense prediction. arXiv preprint arXiv:2310.01403 (2023)"},{"key":"18_CR60","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"18_CR61","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: GroupViT: semantic segmentation emerges from text supervision. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"18_CR62","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"18_CR63","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Learning open-vocabulary semantic segmentation models from natural language supervision. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"18_CR64","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"18_CR65","doi-asserted-by":"crossref","unstructured":"Yi, M., Cui, Q., Wu, H., Yang, C., Yoshie, O., Lu, H.: A simple framework for text-supervised semantic segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00683"},{"key":"18_CR66","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"18_CR67","unstructured":"Yu, Y., et al.: Emergence of segmentation with minimalistic white-box transformers. arXiv preprint arXiv:2308.16271 (2023)"},{"key":"18_CR68","unstructured":"Yuan, L., et\u00a0al.: Florence: a new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)"},{"key":"18_CR69","doi-asserted-by":"crossref","unstructured":"Yun, S., Park, S.H., Seo, P.H., Shin, J.: IFSeg: image-free semantic segmentation via vision-language model. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00290"},{"key":"18_CR70","doi-asserted-by":"crossref","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ADE20K dataset. IJCV 127, 302\u2013321 (2019)","DOI":"10.1007\/s11263-018-1140-0"},{"key":"18_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from clip. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"18_CR72","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. arXiv preprint arXiv:2109.01134 (2021)"},{"key":"18_CR73","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Lei, Y., Zhang, B., Liu, L., Liu, Y.: ZegCLIP: towards adapting clip for zero-shot semantic segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"18_CR74","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, X., Ke, Z., Zhang, W., Lau, R.W.: BiFormer: vision transformer with bi-level routing attention. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"18_CR75","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"18_CR76","unstructured":"Zou, X., et al.: Segment everything everywhere all at once. arXiv preprint arXiv:2304.06718 (2023)"}],"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\/978-3-031-72664-4_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T08:28:51Z","timestamp":1732955331000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72664-4_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726637","9783031726644"],"references-count":76,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72664-4_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 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"}}]}}