{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T22:04:02Z","timestamp":1778537042774,"version":"3.51.4"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200588","type":"print"},{"value":"9783031200595","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20059-5_36","type":"book-chapter","created":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:02:50Z","timestamp":1666972970000},"page":"627-643","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Referring Object Manipulation of\u00a0Natural Images with\u00a0Conditional Classifier-Free Guidance"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4731-3074","authenticated-orcid":false,"given":"Myungsub","family":"Choi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Qin, Y., Wonka, P.: Image2StyleGAN: how to embed images into the StyleGAN latent space? In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00453"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Abdal, R., Qin, Y., Wonka, P.: Image2StyleGAN++: how to edit the embedded images? In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. arXiv:2111.14818 (2021)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"36_CR5","unstructured":"Bau, D., et al.: Paint by word. arXiv:2103.10951 (2021)"},{"key":"36_CR6","doi-asserted-by":"publisher","unstructured":"Bisong, E.: Google colaboratory. In: Building Machine Learning and Deep Learning Models on Google Cloud Platform: A Comprehensive Guide for Beginners, pp. 59\u201364. Apress, Berkeley (2019). https:\/\/doi.org\/10.1007\/978-1-4842-4470-8_7","DOI":"10.1007\/978-1-4842-4470-8_7"},{"key":"36_CR7","unstructured":"Crowson, K.: Clip guided diffusion $$512\\times 512$$, secondary model method(2021). https:\/\/twitter.com\/RiversHaveWings\/status\/1462859669454536711"},{"key":"36_CR8","unstructured":"Crowson, K.: Clip guided diffusion HQ $$256\\times 256$$ (2021). https:\/\/colab.research.google.com\/drive\/12a_Wrfi2_gwwAuN3VvMTwVMz9TfqctNj"},{"key":"36_CR9","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Dong, H., Yu, S., Wu, C., Guo, Y.: Semantic image synthesis via adversarial learning. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.608"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Feng, G., Hu, Z., Zhang, L., Lu, H.: Encoder fusion network with co-attention embedding for referring image segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Gal, R., Patashnik, O., Maron, H., Chechik, G., Cohen-Or, D.: StyleGAN-NADA: CLIP-guided domain adaptation of image generators. arXiv:2108.00946 (2021)","DOI":"10.1145\/3528223.3530164"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Goh, G., et al.: Multimodal neurons in artificial neural networks. Distill (2021). https:\/\/distill.pub\/2021\/multimodal-neurons","DOI":"10.23915\/distill.00030"},{"key":"36_CR15","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"36_CR16","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021)"},{"issue":"8","key":"36_CR17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"36_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-319-46448-0_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Hu","year":"2016","unstructured":"Hu, R., Rohrbach, M., Darrell, T.: Segmentation from natural language expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 108\u2013124. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_7"},{"key":"36_CR19","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Jing, Y., Kong, T., Wang, W., Wang, L., Li, L., Tan, T.: Locate then segment: a strong pipeline for referring image segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR-modulated detection for end-to-end multi-modal understanding. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"36_CR23","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv:1710.10196 (2017)"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"36_CR25","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"36_CR26","doi-asserted-by":"crossref","unstructured":"Kim, G., Ye, J.C.: DiffusionCLIP: text-guided diffusion models for robust image manipulation. arXiv:2110.02711 (2021)","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"36_CR27","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv:1312.6114 (2013)"},{"key":"36_CR28","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv:1411.2539 (2014)"},{"key":"36_CR29","doi-asserted-by":"crossref","unstructured":"Kocasari, U., Dirik, A., Tiftikci, M., Yanardag, P.: StyleMC: multi-channel based fast text-guided image generation and manipulation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2022)","DOI":"10.1109\/WACV51458.2022.00350"},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.H.: ManiGAN: text-guided image manipulation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Referring image segmentation via recurrent refinement networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00602"},{"key":"36_CR32","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":"36_CR33","doi-asserted-by":"crossref","unstructured":"Liu, C., Lin, Z., Shen, X., Yang, J., Lu, X., Yuille, A.: Recurrent multimodal interaction for referring image segmentation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"36_CR34","unstructured":"Liu, X., Gong, C., Wu, L., Zhang, S., Su, H., Liu, Q.: FuseDream: training-free text-to-image generation with improved CLIP+GAN space optimization. arXiv:2112.01573 (2021)"},{"key":"36_CR35","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv:1411.1784 (2014)"},{"key":"36_CR36","unstructured":"Nam, S., Kim, Y., Kim, S.J.: Text-adaptive generative adversarial networks: manipulating images with natural language. In: NeurIPS (2018)"},{"key":"36_CR37","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv:2112.10741 (2021)"},{"key":"36_CR38","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML (2021)"},{"key":"36_CR39","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing, pp. 722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"36_CR40","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. arXiv:1912.01703 (2019)"},{"key":"36_CR41","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: StyleCLIP: text-driven manipulation of StyleGAN imagery. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"36_CR42","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv:2103.00020 (2021)"},{"key":"36_CR43","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML (2021)"},{"key":"36_CR44","unstructured":"Razavi, A., van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. arXiv:1906.00446 (2019)"},{"key":"36_CR45","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: ICML (2016)"},{"key":"36_CR46","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"36_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-030-01231-1_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Shi","year":"2018","unstructured":"Shi, H., Li, H., Meng, F., Wu, Q.: Key-word-aware network for referring expression image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 38\u201354. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_3"},{"key":"36_CR48","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"36_CR49","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"36_CR50","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset (2011)"},{"key":"36_CR51","doi-asserted-by":"crossref","unstructured":"Wu, C., Lin, Z., Cohen, S., Bui, T., Maji, S.: PhraseCut: language-based image segmentation in the wild. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"36_CR52","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lischinski, D., Shechtman, E.: StyleSpace analysis: disentangled controls for StyleGAN image generation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"36_CR53","doi-asserted-by":"crossref","unstructured":"Xia, W., Yang, Y., Xue, J.H., Wu, B.: TediGAN: text-guided diverse face image generation and manipulation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"36_CR54","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"36_CR55","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Predict, prevent, and evaluate: disentangled text-driven image manipulation empowered by pre-trained vision-language model. arXiv:2111.13333 (2021)","DOI":"10.1109\/CVPR52688.2022.01769"},{"key":"36_CR56","doi-asserted-by":"crossref","unstructured":"Yang, S., Xia, M., Li, G., Zhou, H.Y., Yu, Y.: Bottom-up shift and reasoning for referring image segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"36_CR57","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: LAVT: language-aware vision transformer for referring image segmentation. arXiv:2112.02244 (2021)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"36_CR58","doi-asserted-by":"crossref","unstructured":"Ye, L., Rochan, M., Liu, Z., Wang, Y.: Cross-modal self-attention network for referring image segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01075"},{"key":"36_CR59","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MAttNet: modular attention network for referring expression comprehension. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"36_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.629"},{"issue":"8","key":"36_CR61","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2018","unstructured":"Zhang, H., et al.: StackGAN++: realistic image synthesis with stacked generative adversarial networks. IEEE TPAMI 41(8), 1947\u20131962 (2018)","journal-title":"IEEE TPAMI"},{"key":"36_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, L., Chen, Q., Hu, B., Jiang, S.: Text-guided neural image inpainting. In: ACM MM (2020)","DOI":"10.1145\/3394171.3414017"},{"key":"36_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, T., Tseng, H.Y., Jiang, L., Yang, W., Lee, H., Essa, I.: Text as neural operator: image manipulation by text instruction. In: ACM MM (2021)","DOI":"10.1145\/3474085.3475343"},{"key":"36_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1007\/978-3-030-58520-4_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Zhu","year":"2020","unstructured":"Zhu, J., Shen, Y., Zhao, D., Zhou, B.: In-domain GAN inversion for real image editing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 592\u2013608. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_35"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20059-5_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:15:15Z","timestamp":1666973715000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20059-5_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200588","9783031200595"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20059-5_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"29 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}