{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T16:15:14Z","timestamp":1758125714588,"version":"3.40.3"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031732348"},{"type":"electronic","value":"9783031732355"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-73235-5_18","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:01:53Z","timestamp":1727589713000},"page":"319-335","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SAIR: Learning Semantic-Aware Implicit Representation"],"prefix":"10.1007","author":[{"given":"Canyu","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Xiaoguang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Qing","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Song","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"18_CR1","unstructured":"Bar, A., Gandelsman, Y., Darrell, T., Globerson, A., Efros, A.: Visual prompting via image inpainting. In: NeurIPS, vol. 35, pp. 25005\u201325017 (2022)"},{"key":"18_CR2","unstructured":"Cao, Y., Li, T., Cao, X., Tsang, I., Liu, Y., Guo, Q.: IRAD: implicit representation-driven image resampling against adversarial attacks. In: ICLR (2024)"},{"key":"18_CR3","unstructured":"Chen, H., He, B., Wang, H., Ren, Y., Lim, S.N., Shrivastava, A.: Nerv: neural representations for videos. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) NeurIPS, vol.\u00a034, pp. 21557\u201321568. Curran Associates, Inc. (2021)"},{"key":"18_CR4","unstructured":"Chen, J., et al.: LRR: language-driven resamplable continuous representation against adversarial tracking attacks. In: ICLR (2024)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, S., Wang, X.: Learning continuous image representation with local implicit image function. In: CVPR, pp. 8628\u20138638 (2021)","DOI":"10.1109\/CVPR46437.2021.00852"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, H.: Learning implicit fields for generative shape modeling. In: CVPR, pp. 5939\u20135948 (2019)","DOI":"10.1109\/CVPR.2019.00609"},{"key":"18_CR7","unstructured":"Feng, T., Feng, W., Li, W., Lin, D.: Cross-image context for single image inpainting. In: NeurIPS, vol. 35, pp. 1474\u20131487 (2022)"},{"key":"18_CR8","unstructured":"Grattarola, D., Vandergheynst, P.: Generalised implicit neural representations. arXiv preprint arXiv:2205.15674 (2022)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Guo, Q., Li, X., Juefei-Xu, F., Yu, H., Liu, Y., Wang, S.: Jpgnet: joint predictive filtering and generative network for image inpainting. In: ACM International Multimedia, pp. 386\u2013394 (2021)","DOI":"10.1145\/3474085.3475170"},{"key":"18_CR10","unstructured":"Guo, Z., Lan, C., Zhang, Z., Chen, Z., Lu, Y.: Versatile neural processes for learning implicit neural representations. arXiv preprint arXiv:2301.08883 (2023)"},{"key":"18_CR11","unstructured":"Ho, C.H., Vasconcelos, N.: Disco: adversarial defense with local implicit functions. arXiv preprint arXiv:2212.05630 (2022)"},{"key":"18_CR12","unstructured":"Hsu, J., Gu, J., Wu, G., Chiu, W., Yeung, S.: Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations. In: NeurIPS, vol. 34, pp. 5112\u20135123 (2021)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Liu, Z., Wu, L., Luo, P.: Maskgan: towards diverse and interactive facial image manipulation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Lee, J., Jin, K.H.: Local texture estimator for implicit representation function. In: CVPR, pp. 1929\u20131938 (2022)","DOI":"10.1109\/CVPR52688.2022.00197"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, N., Zhang, L., Du, B., Tao, D.: Recurrent feature reasoning for image inpainting. In: CVPR, pp. 7760\u20137768 (2020)","DOI":"10.1109\/CVPR42600.2020.00778"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Li, W., Lin, Z., Zhou, K., Qi, L., Wang, Y., Jia, J.: Mat: mask-aware transformer for large hole image inpainting. In: CVPR, pp. 10758\u201310768 (2022)","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Leveraging inpainting for single-image shadow removal. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13055\u201313064 (2023)","DOI":"10.1109\/ICCV51070.2023.01200"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., Guo, Q., Cai, P., Feng, W., Tsang, I., Wang, S.: Learning restoration is not enough: transfering identical mapping for single-image shadow removal. arXiv preprint arXiv:2305.10640 (2023)","DOI":"10.1109\/ICCV51070.2023.01200"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Li, X., Guo, Q., Lin, D., Li, P., Feng, W., Wang, S.: Misf: multi-level interactive siamese filtering for high-fidelity image inpainting. In: CVPR, pp. 1869\u20131878 (2022)","DOI":"10.1109\/CVPR52688.2022.00191"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., Min, M.R., Li, K., Xu, C.: Stylet2i: toward compositional and high-fidelity text-to-image synthesis. In: CVPR, pp. 18197\u201318207 (2022)","DOI":"10.1109\/CVPR52688.2022.01766"},{"issue":"2","key":"18_CR22","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1109\/JSTSP.2020.3045627","volume":"15","author":"L Liao","year":"2020","unstructured":"Liao, L., Xiao, J., Wang, Z., Lin, C.W., Satoh, S.: Uncertainty-aware semantic guidance and estimation for image inpainting. IEEE J. Sel. Top. Signal Process. 15(2), 310\u2013323 (2020)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Lim, B., Son, S., Kim, H., Nah, S., Mu\u00a0Lee, K.: Enhanced deep residual networks for single image super-resolution. In: CVPR Workshop, pp. 136\u2013144 (2017)","DOI":"10.1109\/CVPRW.2017.151"},{"key":"18_CR24","unstructured":"Lin, Y., Xie, Y., Chen, D., Xu, Y., Zhu, C., Yuan, L.: Revive: regional visual representation matters in knowledge-based visual question answering. arXiv preprint arXiv:2206.01201 (2022)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Liu, G., Reda, F.A., Shih, K.J., Wang, T.C., Tao, A., Catanzaro, B.: Image inpainting for irregular holes using partial convolutions. In: ECCV, pp. 85\u2013100 (2018)","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.425"},{"issue":"11","key":"18_CR27","doi-asserted-by":"publisher","first-page":"2707","DOI":"10.1007\/s11263-022-01669-7","volume":"130","author":"Y Lu","year":"2022","unstructured":"Lu, Y., et al.: Snowvision: segmenting, identifying, and discovering stamped curve patterns from fragments of pottery. Int. J. Comput. Vision 130(11), 2707\u20132732 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: CVPR, pp. 7086\u20137096 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"issue":"1","key":"18_CR29","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Nazeri, K., Ng, E., Joseph, T., Qureshi, F., Ebrahimi, M.: Edgeconnect: structure guided image inpainting using edge prediction. In: ICCV Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00408"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Ni, M., Li, X., Zuo, W.: NUWA-LIP: language-guided image inpainting with defect-free VQGAN. In: CVPR, pp. 14183\u201314192 (2023)","DOI":"10.1109\/CVPR52729.2023.01363"},{"key":"18_CR32","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":"18_CR33","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, vol. 1, no. 2, p. 3 (2022)"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Ren, Y., Yu, X., Zhang, R., Li, T.H., Liu, S., Li, G.: Structureflow: image inpainting via structure-aware appearance flow. In: CVPR, pp. 181\u2013190 (2019)","DOI":"10.1109\/ICCV.2019.00027"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"18_CR36","unstructured":"Su, K., Chen, M., Shlizerman, E.: Inras: implicit neural representation for audio scenes. In: NeurIPS, vol. 35, pp. 8144\u20138158 (2022)"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Suvorov, R., et al.: Resolution-robust large mask inpainting with fourier convolutions. In: WACV (2022)","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Tao, M., Tang, H., Wu, F., Jing, X.Y., Bao, B.K., Xu, C.: DF-GAN: a simple and effective baseline for text-to-image synthesis. In: CVPR, pp. 16515\u201316525 (2022)","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"18_CR39","unstructured":"Wang, Y., Tao, X., Qi, X., Shen, X., Jia, J.: Image inpainting via generative multi-column convolutional neural networks. In: NeurIPS, vol. 31 (2018)"},{"key":"18_CR40","unstructured":"Xie, Z., Zhang, J., Li, W., Zhang, F., Zhang, L.: S-nerf: neural radiance fields for street views. arXiv preprint arXiv:2303.00749 (2023)"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Groupvit: semantic segmentation emerges from text supervision. In: CVPR, pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Tap: text-aware pre-training for text-VQA and text-caption. In: CVPR, pp. 8751\u20138761 (2021)","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"18_CR43","unstructured":"Yariv, L., Gu, J., Kasten, Y., Lipman, Y.: Volume rendering of neural implicit surfaces. In: NeurIPS, vol. 34, pp. 4805\u20134815 (2021)"},{"key":"18_CR44","unstructured":"Yin, F., Liu, W., Huang, Z., Cheng, P., Chen, T., Yu, G.: Coordinates are not lonely\u2013codebook prior helps implicit neural 3D representations. arXiv preprint arXiv:2210.11170 (2022)"},{"key":"18_CR45","unstructured":"Zhang, C., et al.: Superinpaint: learning detail-enhanced attentional implicit representation for super-resolutional image inpainting. arXiv preprint arXiv:2307.14489 (2023)"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, L., Chen, Q., Hu, B., Jiang, S.: Text-guided neural image inpainting. In: ACM Multimedia, pp. 1302\u20131310 (2020)","DOI":"10.1145\/3394171.3414017"},{"key":"18_CR47","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 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"18_CR48","unstructured":"Zhao, M., et\u00a0al.: Towards video text visual question answering: benchmark and baseline. In: Thirty-Sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2022)"},{"key":"18_CR49","unstructured":"Zhenxing, M., Xu, D.: Switch-nerf: learning scene decomposition with mixture of experts for large-scale neural radiance fields. In: ICLR (2022)"},{"key":"18_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: CVPR, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"18_CR51","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":"18_CR52","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, pp. 11175\u201311185 (2023)","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"18_CR53","unstructured":"Zhu, Y., et al.: One model to edit them all: free-form text-driven image manipulation with semantic modulations. In: NeurIPS, vol. 35, pp. 25146\u201325159 (2022)"}],"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\/978-3-031-73235-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:16:01Z","timestamp":1732828561000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73235-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031732348","9783031732355"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73235-5_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}