{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T05:07:34Z","timestamp":1764997654338,"version":"3.40.3"},"publisher-location":"Cham","reference-count":84,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726323"},{"type":"electronic","value":"9783031726330"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-72633-0_5","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T07:56:21Z","timestamp":1732175781000},"page":"78-97","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A Simple Latent Diffusion Approach for\u00a0Panoptic Segmentation and\u00a0Mask Inpainting"],"prefix":"10.1007","author":[{"given":"Wouter","family":"Van Gansbeke","sequence":"first","affiliation":[]},{"given":"Bert","family":"De Brabandere","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Abu\u00a0Alhaija, H., Mustikovela, S.K., Mescheder, L., Geiger, A., Rother, C.: Augmented reality meets computer vision: efficient data generation for urban driving scenes. Int. J. Comput. Vision (IJCV) (2018)","DOI":"10.5244\/C.31.81"},{"key":"5_CR2","unstructured":"Amit, T., Shaharbany, T., Nachmani, E., Wolf, L.: SegDiff: Image segmentation with diffusion probabilistic models. arXiv preprint arXiv:2112.00390 (2021)"},{"key":"5_CR3","unstructured":"Asiedu, E.B., Kornblith, S., Chen, T., Parmar, N., Minderer, M., Norouzi, M.: Decoder denoising pretraining for semantic segmentation. arXiv preprint arXiv:2205.11423 (2022)"},{"key":"5_CR4","unstructured":"Bar, A., Gandelsman, Y., Darrell, T., Globerson, A., Efros, A.: Visual prompting via image inpainting. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"5_CR5","unstructured":"Baranchuk, D., Rubachev, I., Voynov, A., Khrulkov, V., Babenko, A.: Label-efficient semantic segmentation with diffusion models. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS\u2013improving object detection with one line of code. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/ICCV.2017.593"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"5_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Chen, T., Li, L., Saxena, S., Hinton, G., Fleet, D.J.: A generalist framework for panoptic segmentation of images and videos. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"5_CR10","unstructured":"Chen, T., Saxena, S., Li, L., Fleet, D.J., Hinton, G.: Pix2Seq: a language modeling framework for object detection. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"5_CR11","unstructured":"Chen, T., Saxena, S., Li, L., Lin, T.Y., Fleet, D.J., Hinton, G.E.: A unified sequence interface for vision tasks. In: Advances in Neural Information Processing Systems (2022)"},{"key":"5_CR12","unstructured":"Chen, T., Zhang, R., Hinton, G.: Analog bits: generating discrete data using diffusion models with self-conditioning. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Cheng, B., et al.: Panoptic-DeepLab: a simple, strong, and fast baseline for bottom-up panoptic segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"5_CR14","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"5_CR15","unstructured":"Cheng, B., Schwing, A.G., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Chiu, M.T., et\u00a0al.: Agriculture-vision: a large aerial image database for agricultural pattern analysis. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00290"},{"key":"5_CR17","unstructured":"Cho, J.H., Mall, U., Bala, K., Hariharan, B.: PiCIE: unsupervised semantic segmentation using invariance and equivariance in clustering. In: CVPR (2021)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"5_CR19","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"5_CR20","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"5_CR21","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 107, 3\u201311 (2018)","journal-title":"Neural Netw."},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"5_CR24","unstructured":"Grauman, K., et\u00a0al.: Ego4D: around the world in 3,000 hours of egocentric video. arXiv preprint arXiv:2110.07058 (2021)"},{"key":"5_CR25","unstructured":"Gu, Z., Chen, H., Xu, Z., Lan, J., Meng, C., Wang, W.: DiffusionInst: diffusion model for instance segmentation. arXiv preprint arXiv:2212.02773 (2022)"},{"key":"5_CR26","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR29","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"5_CR30","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Hosang, J., Benenson, R., Schiele, B.: Learning non-maximum suppression. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.685"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Ji, Y., et al.: DDP: diffusion model for dense visual prediction. arXiv preprint arXiv:2303.17559 (2023)","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"5_CR33","unstructured":"Jia, X., De\u00a0Brabandere, B., Tuytelaars, T., Van\u00a0Gool, L.: Dynamic filter networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2016)"},{"key":"5_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"5_CR35","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: International Conference on Learning Representations (ICLR) (2014)"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"5_CR38","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., Girshick, R.: PointRend: image segmentation as rendering. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"5_CR40","unstructured":"Kolesnikov, A., Susano\u00a0Pinto, A., Beyer, L., Zhai, X., Harmsen, J., Houlsby, N.: UViM: a unified modeling approach for vision with learned guiding codes. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"issue":"1\u20132","key":"5_CR41","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Q."},{"key":"5_CR42","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 (ICML) (2022)"},{"key":"5_CR43","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":"5_CR44","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"5_CR46","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"5_CR47","unstructured":"Lu, J., Clark, C., Zellers, R., Mottaghi, R., Kembhavi, A.: Unified-IO: a unified model for vision, language, and multi-modal tasks. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"5_CR48","unstructured":"Menze, B.H., et\u00a0al.: The multimodal brain tumor image segmentation benchmark (brats). IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI) (2014)"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Minaee, S., Boykov, Y.Y., Porikli, F., Plaza, A.J., Kehtarnavaz, N., Terzopoulos, D.: Image segmentation using deep learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI) (2021)","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"5_CR50","unstructured":"Mizrahi, D., et al.: 4M: massively multimodal masked modeling. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"5_CR51","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: International Conference on Machine Learning (ICML) (2022)"},{"key":"5_CR52","unstructured":"van\u00a0den Oord, A., Vinyals, O., kavukcuoglu, k.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"5_CR53","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"5_CR54","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"5_CR55","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"5_CR56","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"5_CR57","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2015)"},{"key":"5_CR58","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"5_CR59","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":"5_CR60","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"5_CR61","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning (ICML) (2015)"},{"key":"5_CR62","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"5_CR63","unstructured":"Song, Y., Ermon, S.: Improved techniques for training score-based generative models. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"5_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/978-3-319-67558-9_28","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"CH Sudre","year":"2017","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., et al. (eds.) DLMIA\/ML-CDS -2017. LNCS, vol. 10553, pp. 240\u2013248. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-67558-9_28"},{"key":"5_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-030-58452-8_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Tian","year":"2020","unstructured":"Tian, Z., Shen, C., Chen, H.: Conditional convolutions for instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 282\u2013298. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_17"},{"key":"5_CR66","unstructured":"Van Den\u00a0Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning (ICML) (2016)"},{"key":"5_CR67","unstructured":"Van\u00a0Gansbeke, W., Vandenhende, S., Georgoulis, S., Van\u00a0Gool, L.: Revisiting contrastive methods for unsupervised learning of visual representations. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"5_CR68","doi-asserted-by":"crossref","unstructured":"Van\u00a0Gansbeke, W., Vandenhende, S., Georgoulis, S., Van\u00a0Gool, L.: Unsupervised semantic segmentation by contrasting object mask proposals. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"5_CR69","unstructured":"Van\u00a0Gansbeke, W., Vandenhende, S., Van\u00a0Gool, L.: Discovering object masks with transformers for unsupervised semantic segmentation. arXiv preprint arXiv:2206.06363 (2022)"},{"key":"5_CR70","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"5_CR71","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"5_CR72","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, W., Cao, Y., Shen, C., Huang, T.: Images speak in images: a generalist painter for in-context visual learning. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"5_CR73","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: FreeSOLO: learning to segment objects without annotations. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01378"},{"key":"5_CR74","unstructured":"Wang, X., Zhang, R., Kong, T., Li, L., Shen, C.: SOLOv2: dynamic and fast instance segmentation. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"5_CR75","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00305"},{"key":"5_CR76","unstructured":"Wang, Z., et\u00a0al.: In-context learning unlocked for diffusion models. In: Advances in Neural Information Processing Systems (NeurIPS) (2024)"},{"key":"5_CR77","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"5_CR78","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: UPSNet: a unified panoptic segmentation network. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00902"},{"key":"5_CR79","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"5_CR80","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1007\/978-3-031-19818-2_17","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Q Yu","year":"2022","unstructured":"Yu, Q., et al.: k-means mask transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13689, pp. 288\u2013307. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_17"},{"key":"5_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"5_CR82","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"5_CR83","unstructured":"Zhang, W., Pang, J., Chen, K., Loy, C.C.: K-net: towards unified image segmentation. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"5_CR84","doi-asserted-by":"crossref","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ADE20K dataset. Int. J. Comput. Vision (IJCV) (2019)","DOI":"10.1007\/s11263-018-1140-0"}],"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\/978-3-031-72633-0_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T08:06:56Z","timestamp":1732176416000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72633-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031726323","9783031726330"],"references-count":84,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72633-0_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 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"}}]}}