{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:05:57Z","timestamp":1784131557952,"version":"3.55.0"},"publisher-location":"Cham","reference-count":89,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736674","type":"print"},{"value":"9783031736681","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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\/978-3-031-73668-1_10","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:02:24Z","timestamp":1733018544000},"page":"161-180","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Exploring Phrase-Level Grounding with\u00a0Text-to-Image Diffusion Model"],"prefix":"10.1007","author":[{"given":"Danni","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruohan","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiwei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haowei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,1]]},"reference":[{"key":"10_CR1","unstructured":"Baranchuk, D., Rubachev, I., Voynov, A., Khrulkov, V., Babenko, A.: Label-efficient semantic segmentation with diffusion models. arXiv preprint arXiv:2112.03126 (2021)"},{"key":"10_CR2","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"10_CR3","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":"10_CR4","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., Luo, P.: Diffusiondet: diffusion model for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19830\u201319843 (2023)","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y.H., Chen, W.Y., Chen, Y.T., Tsai, B.C., Frank\u00a0Wang, Y.C., Sun, M.: No more discrimination: cross city adaptation of road scene segmenters. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1992\u20132001 (2017)","DOI":"10.1109\/ICCV.2017.220"},{"key":"10_CR6","unstructured":"Cho, J.H., Mall, U., Bala, K., Hariharan, B.: Picie: unsupervised semantic segmentation using invariance and equivariance in clustering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16794\u201316804 (2021)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"10_CR8","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":"10_CR9","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.S., Dai, D.: Decoupling zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11583\u201311592 (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Ding, Z., et al.: PPMN: pixel-phrase matching network for one-stage panoptic narrative grounding. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5537\u20135546 (2022)","DOI":"10.1145\/3503161.3548086"},{"key":"10_CR11","unstructured":"Dockhorn, T., Vahdat, A., Kreis, K.: Score-based generative modeling with critically-damped langevin diffusion. arXiv preprint arXiv:2112.07068 (2021)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Ehsani, K., Mottaghi, R., Farhadi, A.: Segan: segmenting and generating the invisible. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6144\u20136153 (2018)","DOI":"10.1109\/CVPR.2018.00643"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Feng, Q., Gadde, R., Liao, W., Ramon, E., Martinez, A.: Network-free, unsupervised semantic segmentation with synthetic images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23602\u201323610 (2023)","DOI":"10.1109\/CVPR52729.2023.02260"},{"key":"10_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-73973-7_11","volume-title":"Structural, Syntactic, and Statistical Pattern Recognition","author":"D Galeev","year":"2021","unstructured":"Galeev, D., Sofiiuk, K., Rukhovich, D., Romanov, M., Barinova, O., Konushin, A.: Learning high-resolution domain-specific representations with a GAN generator. In: Torsello, A., Rossi, L., Pelillo, M., Biggio, B., Robles-Kelly, A. (eds.) S+SSPR 2021. LNCS, vol. 12644, pp. 108\u2013118. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-73973-7_11"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez, C., Ayobi, N., Hern\u00e1ndez, I., Hern\u00e1ndez, J., Pont-Tuset, J., Arbel\u00e1ez, P.: Panoptic narrative grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1364\u20131373 (2021)","DOI":"10.1109\/ICCV48922.2021.00140"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez, C., Ayobi, N., Hern\u00e1ndez, I., Pont-Tuset, J., Arbel\u00e1ez, P.: Piglet: pixel-level grounding of language expressions with transformers. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3286760"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Guo, T., Wang, H., Ma, Y., Ji, J., Sun, X.: Improving panoptic narrative grounding by harnessing semantic relationships and visual confirmation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 1985\u20131993 (2024)","DOI":"10.1609\/aaai.v38i3.27969"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR20","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":"10_CR21","unstructured":"Hoffman, J., Wang, D., Yu, F., Darrell, T.: FCNs in the wild: pixel-level adversarial and constraint-based adaptation. arXiv preprint arXiv:1612.02649 (2016)"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Hui, T., et al.: Enriching phrases with coupled pixel and object contexts for panoptic narrative grounding. arXiv preprint arXiv:2311.01091 (2023)","DOI":"10.24963\/ijcai.2023\/99"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y.: Acquisition of localization confidence for accurate object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 784\u2013799 (2018)","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"10_CR24","unstructured":"Jolicoeur-Martineau, A., Pich\u00e9-Taillefer, R., Combes, R.T.d., Mitliagkas, I.: Adversarial score matching and improved sampling for image generation. arXiv preprint arXiv:2009.05475 (2020)"},{"key":"10_CR25","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.cviu.2017.06.005","volume":"163","author":"K Kafle","year":"2017","unstructured":"Kafle, K., Kanan, C.: Visual question answering: datasets, algorithms, and future challenges. Comput. Vis. Image Underst. 163, 3\u201320 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"10_CR26","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":"10_CR27","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"10_CR28","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"10_CR29","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"10_CR30","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with gaussian edge potentials. In: Advances in Neural Information Processing Systems, vol. 24 (2011)"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Li, A.C., Prabhudesai, M., Duggal, S., Brown, E., Pathak, D.: Your diffusion model is secretly a zero-shot classifier. arXiv preprint arXiv:2303.16203 (2023)","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Li, D., Ling, H., Kim, S.W., Kreis, K., Fidler, S., Torralba, A.: Bigdatasetgan: synthesizing imagenet with pixel-wise annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21330\u201321340 (2022)","DOI":"10.1109\/CVPR52688.2022.02064"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Acseg: adaptive conceptualization for unsupervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7162\u20137172 (2023)","DOI":"10.1109\/CVPR52729.2023.00692"},{"key":"10_CR34","unstructured":"Li, Z., Zhou, Q., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Guiding text-to-image diffusion model towards grounded generation. arXiv preprint arXiv:2301.05221 (2023)"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Li, Z., Zhou, Q., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Open-vocabulary object segmentation with diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7667\u20137676 (2023)","DOI":"10.1109\/ICCV51070.2023.00705"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Lin, Y., Jin, X.B., Wang, Q., Huang, K.: Context does matter: end-to-end panoptic narrative grounding with deformable attention refined matching network. In: 2023 IEEE International Conference on Data Mining (ICDM), pp. 1163\u20131168. IEEE (2023)","DOI":"10.1109\/ICDM58522.2023.00142"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Liu, X., Huang, S., Kang, Y., Chen, H., Wang, D.: Vgdiffzero: text-to-image diffusion models can be zero-shot visual grounders. arXiv preprint arXiv:2309.01141 (2023)","DOI":"10.1109\/ICASSP48485.2024.10445945"},{"key":"10_CR39","unstructured":"Luc, P., Couprie, C., Chintala, S., Verbeek, J.: Semantic segmentation using adversarial networks. arXiv preprint arXiv:1611.08408 (2016)"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Luo, G., et al.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10034\u201310043 (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: Dual-level collaborative transformer for image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 2286\u20132293 (2021)","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"10_CR42","unstructured":"Lutz, S., Amplianitis, K., Smolic, A.: Alphagan: generative adversarial networks for natural image matting. arXiv preprint arXiv:1807.10088 (2018)"},{"key":"10_CR43","unstructured":"Ma, C., et al.: Diffusionseg: adapting diffusion towards unsupervised object discovery. arXiv preprint arXiv:2303.09813 (2023)"},{"key":"10_CR44","unstructured":"Meng, C., et al.: Sdedit: guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)"},{"key":"10_CR45","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1007\/978-3-031-19818-2_42","volume-title":"Computer Vision \u2013 ECCV 2022","author":"M Xu","year":"2022","unstructured":"Xu, M., et al.: A simple baseline for open vocabulary semantic segmentation with pre-trained vision-language model. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13689, pp. 736\u2013753. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_42"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"10_CR47","unstructured":"Nguyen, Q., Vu, T., Tran, A., Nguyen, K.: Dataset diffusion: diffusion-based synthetic data generation for pixel-level semantic segmentation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"10_CR48","unstructured":"Ni, M., Zhang, Y., Feng, K., Li, X., Guo, Y., Zuo, W.: Ref-diff: zero-shot referring image segmentation with generative models. arXiv preprint arXiv:2308.16777 (2023)"},{"key":"10_CR49","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"10_CR50","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10971\u201310980 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"10_CR51","doi-asserted-by":"crossref","unstructured":"Pnvr, K., Singh, B., Ghosh, P., Siddiquie, B., Jacobs, D.: LD-ZNet: a latent diffusion approach for text-based image segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4157\u20134168 (2023)","DOI":"10.1109\/ICCV51070.2023.00384"},{"key":"10_CR52","doi-asserted-by":"crossref","unstructured":"Qian, Z., Ma, Y., Ji, J., Sun, X.: X-refseg3d: enhancing referring 3D instance segmentation via structured cross-modal graph neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 4551\u20134559 (2024)","DOI":"10.1609\/aaai.v38i5.28254"},{"key":"10_CR53","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":"10_CR54","unstructured":"Ren, T., et al.: Grounded SAM: assembling open-world models for diverse visual tasks (2024)"},{"key":"10_CR55","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":"10_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"10_CR57","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR58","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C.: 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":"10_CR59","unstructured":"Shao, Z., Sengupta, S., Li, H., Anastasio, M.A.: Semi-supervised semantic segmentation of cell nuclei via diffusion-based large-scale pre-training and collaborative learning. arXiv preprint arXiv:2308.04578 (2023)"},{"key":"10_CR60","doi-asserted-by":"crossref","unstructured":"Shih, K.J., Singh, S., Hoiem, D.: Where to look: focus regions for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4613\u20134621 (2016)","DOI":"10.1109\/CVPR.2016.499"},{"key":"10_CR61","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":"10_CR62","doi-asserted-by":"crossref","unstructured":"Shin, G., Xie, W., Albanie, S.: Namedmask: distilling segmenters from complementary foundation models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4960\u20134969 (2023)","DOI":"10.1109\/CVPRW59228.2023.00524"},{"key":"10_CR63","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"10_CR64","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"10_CR65","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"10_CR66","first-page":"12438","volume":"33","author":"Y Song","year":"2020","unstructured":"Song, Y., Ermon, S.: Improved techniques for training score-based generative models. Adv. Neural. Inf. Process. Syst. 33, 12438\u201312448 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR67","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"10_CR68","doi-asserted-by":"crossref","unstructured":"Tang, R., et al.: What the DAAM: interpreting stable diffusion using cross attention. arXiv preprint arXiv:2210.04885 (2022)","DOI":"10.18653\/v1\/2023.acl-long.310"},{"key":"10_CR69","doi-asserted-by":"crossref","unstructured":"Tian, J., Aggarwal, L., Colaco, A., Kira, Z., Gonzalez-Franco, M.: Diffuse, attend, and segment: unsupervised zero-shot segmentation using stable diffusion. arXiv preprint arXiv:2308.12469 (2023)","DOI":"10.1109\/CVPR52733.2024.00341"},{"key":"10_CR70","doi-asserted-by":"crossref","unstructured":"Tritrong, N., Rewatbowornwong, P., Suwajanakorn, S.: Repurposing GANs for one-shot semantic part segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4475\u20134485 (2021)","DOI":"10.1109\/CVPR46437.2021.00445"},{"key":"10_CR71","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Hung, W.C., Schulter, S., Sohn, K., Yang, M.H., Chandraker, M.: Learning to adapt structured output space for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7472\u20137481 (2018)","DOI":"10.1109\/CVPR.2018.00780"},{"issue":"4","key":"10_CR72","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2016","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 652\u2013663 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR73","unstructured":"Wang, H., et al.: Nice: improving panoptic narrative detection and segmentation with cascading collaborative learning. arXiv preprint arXiv:2310.10975 (2023)"},{"key":"10_CR74","doi-asserted-by":"crossref","unstructured":"Wang, H., Ji, J., Zhou, Y., Wu, Y., Sun, X.: Towards real-time panoptic narrative grounding by an end-to-end grounding network. arXiv preprint arXiv:2301.03160 (2023)","DOI":"10.1609\/aaai.v37i2.25350"},{"key":"10_CR75","doi-asserted-by":"publisher","unstructured":"Wang, X., Zhang, X., Cao, Y., Wang, W., Shen, C., Huang, T.: Seggpt: towards segmenting everything in context. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1130\u20131140 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00110","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"10_CR76","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.cviu.2017.05.001","volume":"163","author":"Q Wu","year":"2017","unstructured":"Wu, Q., Teney, D., Wang, P., Shen, C., Dick, A., Van Den Hengel, A.: Visual question answering: a survey of methods and datasets. Comput. Vis. Image Underst. 163, 21\u201340 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"10_CR77","doi-asserted-by":"crossref","unstructured":"Wu, W., Zhao, Y., Shou, M.Z., Zhou, H., Shen, C.: Diffumask: synthesizing images with pixel-level annotations for semantic segmentation using diffusion models. arXiv preprint arXiv:2303.11681 (2023)","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"10_CR78","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":"10_CR79","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"10_CR80","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1007\/978-3-031-19818-2_42","volume-title":"European Conference on Computer Vision","author":"M Xu","year":"2022","unstructured":"Xu, M., et al.: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13689, pp. 736\u2013753. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_42"},{"key":"10_CR81","unstructured":"Yang, D., et al.: Sam as the guide: mastering pseudo-label refinement in semi-supervised referring expression segmentation. arXiv preprint arXiv:2406.01451 (2024)"},{"key":"10_CR82","doi-asserted-by":"crossref","unstructured":"Yang, D., et al.: Semi-supervised panoptic narrative grounding. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 7164\u20137174 (2023)","DOI":"10.1145\/3581783.3612259"},{"key":"10_CR83","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18155\u201318165 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"10_CR84","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"10_CR85","doi-asserted-by":"crossref","unstructured":"Yu, S., Seo, P.H., Son, J.: Zero-shot referring image segmentation with global-local context features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19456\u201319465 (2023)","DOI":"10.1109\/CVPR52729.2023.01864"},{"key":"10_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Datasetgan: efficient labeled data factory with minimal human effort. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10145\u201310155 (2021)","DOI":"10.1109\/CVPR46437.2021.01001"},{"key":"10_CR87","unstructured":"Zhou, B., Tian, Y., Sukhbaatar, S., Szlam, A., Fergus, R.: Simple baseline for visual question answering. arXiv preprint arXiv:1512.02167 (2015)"},{"key":"10_CR88","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11175\u201311185 (2023)","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"10_CR89","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"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\/978-3-031-73668-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:08:32Z","timestamp":1733018912000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73668-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"ISBN":["9783031736674","9783031736681"],"references-count":89,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73668-1_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"assertion":[{"value":"1 December 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"}}]}}