{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T10:04:53Z","timestamp":1781777093326,"version":"3.54.5"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T00:00:00Z","timestamp":1721606400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T00:00:00Z","timestamp":1721606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Fundation of China","doi-asserted-by":"crossref","award":["62106080"],"award-info":[{"award-number":["62106080"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11263-024-02191-8","type":"journal-article","created":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T06:01:50Z","timestamp":1721628110000},"page":"151-172","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["FADE: A Task-Agnostic Upsampling Operator for Encoder\u2013Decoder Architectures"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3854-8664","authenticated-orcid":false,"given":"Hao","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1510-6196","authenticated-orcid":false,"given":"Wenze","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6692-0913","authenticated-orcid":false,"given":"Hongtao","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9223-1863","authenticated-orcid":false,"given":"Zhiguo","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,22]]},"reference":[{"issue":"12","key":"2191_CR1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell, 39(12), 2481\u20132495.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2191_CR2","doi-asserted-by":"crossref","unstructured":"Borenstein, E., & Ullman, S. (2002). Class-specific, top-down segmentation. Proc (pp. 109\u2013122). European Conference on Computer Vision: Springer.","DOI":"10.1007\/3-540-47967-8_8"},{"key":"2191_CR3","doi-asserted-by":"crossref","unstructured":"Bulo, S.R., Porzi, L., & Kontschieder, P. (2018). In-place activated batchnorm for memory-optimized training of dnns. In: Proceedings of the IEEE conference on computer vision pattern Recognition, pp. 5639\u20135647.","DOI":"10.1109\/CVPR.2018.00591"},{"key":"2191_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE International Conference Computer Vision, pp. 9650\u20139660.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2191_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2191_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, B., Girshick, R., Doll\u00e1r, P., Berg, A.C., & Kirillov, A, (2021). Boundary iou: Improving object-centric image segmentation evaluation. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 15334\u201315342.","DOI":"10.1109\/CVPR46437.2021.01508"},{"key":"2191_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, T., Wang, X., Huang, L., & Liu, W. (2020). Boundary-preserving mask r-cnn. Proc (pp. 660\u2013676). European Conference on Computer Vision: Springer.","DOI":"10.1007\/978-3-030-58568-6_39"},{"key":"2191_CR8","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Bahdanau, D., & Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv Comput Res Repository.","DOI":"10.3115\/v1\/W14-4012"},{"key":"2191_CR9","doi-asserted-by":"crossref","unstructured":"Dai, Y., Lu, H., & Shen, C. (2021). Learning affinity-aware upsampling for deep image matting. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 6841\u20136850.","DOI":"10.1109\/CVPR46437.2021.00677"},{"issue":"2","key":"2191_CR10","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","volume":"38","author":"C Dong","year":"2015","unstructured":"Dong, C., Loy, C. C., He, K., & Tang, X. (2015). Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell, 38(2), 295\u2013307.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2191_CR11","unstructured":"Eigen, D., Puhrsch, C., & Fergus, R. (2014). Depth map prediction from a single image using a multi-scale deep network. In: Annual Conference on Neural Information Processing Systems, pp. 2366\u20132374."},{"issue":"2","key":"2191_CR12","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (VOC) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"2191_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"2191_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Sun, J., & Tang, X. (2010). Guided image filtering. Proc (pp. 1\u201314). European Conference on Computer Vision: Springer.","DOI":"10.1007\/978-3-642-15549-9_1"},{"key":"2191_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2191_CR16","doi-asserted-by":"crossref","unstructured":"He. K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask R-CNN. In: Proceedings of the IEEE conference on computer vision, pp. 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"2191_CR17","doi-asserted-by":"crossref","unstructured":"Huang, S., Lu, Z., Cheng, R., & He, C. (2021). Fapn: Feature-aligned pyramid network for dense image prediction. In: Proceedings of the IEEE conference on computer vision, pp. 864\u2013873.","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"2191_CR18","doi-asserted-by":"crossref","unstructured":"Ignatov, A., Timofte, R., Denna, M., & Younes, A. (2021). Real-time quantized image super-resolution on mobile npus, mobile ai 2021 challenge: Report. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, Workshops, pp. 2525\u20132534.","DOI":"10.1109\/CVPRW53098.2021.00286"},{"key":"2191_CR19","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., & Girshick, R. (2020). Pointrend: Image segmentation as rendering. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 9799\u20139808.","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"2191_CR20","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., Dollar, P., & Girshick, R. (2023). Segment anything. In: Proceedings of the IEEE conference on computer vision, pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2191_CR21","unstructured":"Lee, J.H., Han, M.K., Ko, D.W., & Suh, I.H. (2019). From big to small: Multi-scale local planar guidance for monocular depth estimation. arXiv Comput Res Repository."},{"key":"2191_CR22","doi-asserted-by":"crossref","unstructured":"Li, X., Li, X., Zhang, L., Cheng, G., Shi, J., Lin, Z., Tan, S., & Tong, Y. (2020). Improving semantic segmentation via decoupled body and edge supervision. Proc (pp. 435\u2013452). European Conference on Computer Vision: Springer.","DOI":"10.1007\/978-3-030-58520-4_26"},{"key":"2191_CR23","doi-asserted-by":"crossref","unstructured":"Li, X., You, A., Zhu, Z., Zhao, H., Yang, M., Yang, K., Tan, S., & Tong, Y. (2020). Semantic flow for fast and accurate scene parsing. Proc (pp. 775\u2013793). European Conference on Computer Vision: Springer.","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"2191_CR24","doi-asserted-by":"publisher","first-page":"11418","DOI":"10.1609\/aaai.v34i07.6805","volume":"34","author":"X Li","year":"2020","unstructured":"Li, X., Zhao, H., Han, L., Tong, Y., Tan, S., & Yang, K. (2020). Gated fully fusion for semantic segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 11418\u201311425.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"2","key":"2191_CR25","first-page":"1","volume":"132","author":"X Li","year":"2023","unstructured":"Li, X., Zhang, J., Yang, Y., Cheng, G., Yang, K., Tong, Y., & Tao, D. (2023). SFNet: Faster and accurate semantic segmentation via semantic flow. International Journal of Computer Vision, 132(2), 1\u201324.","journal-title":"International Journal of Computer Vision"},{"key":"2191_CR26","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., & Reid, I. (2017a). RefineNet: Multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 1925\u20131934.","DOI":"10.1109\/CVPR.2017.549"},{"key":"2191_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan. D., Doll\u00e1r, P., & Zitnick, C.L. (2014). Microsoft coco: Common objects in context. In: Proceedings of the European Conference on Computer Vision, pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2191_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017b). Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"2191_CR29","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., & Jia, J. (2018). Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 8759\u20138768.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"2191_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, J., Pang, Y., Nie, D., & Yap, P.T. (2023). The devil is in the upsampling: Architectural decisions made simpler for denoising with deep image prior. In: Proceedings of the IEEE conference on computer vision, pp. 12408\u201312417.","DOI":"10.1109\/ICCV51070.2023.01140"},{"key":"2191_CR31","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2191_CR32","doi-asserted-by":"crossref","unstructured":"Lu, H., Dai, Y., Shen, C., & Xu, S. (2019). Indices matter: Learning to index for deep image matting. In: Proceedings of the IEEE conference on computer vision, pp. 3266\u20133275.","DOI":"10.1109\/ICCV.2019.00336"},{"issue":"1","key":"2191_CR33","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1109\/TPAMI.2020.3004474","volume":"44","author":"H Lu","year":"2022","unstructured":"Lu, H., Dai, Y., Shen, C., & Xu, S. (2022). Index networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(1), 242\u2013255.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2191_CR34","doi-asserted-by":"crossref","unstructured":"Lu, H., Liu, W., Fu, H., & Cao, Z. (2022b). Fade: Fusing the assets of decoder and encoder for task-agnostic upsampling. In: Proceedings of the European Conference on Computer Vision, pp. 231\u2013247.","DOI":"10.1007\/978-3-031-19812-0_14"},{"key":"2191_CR35","unstructured":"Lu, H., Liu, W., Ye, Z., Fu, H., Liu, Y., & Cao, Z. (2022c). SAPA: Similarity-aware point affiliation for feature upsampling. In: Proceedings of the Annual Conference on Neural Information Processing Systems, pp. 20889\u201320901."},{"key":"2191_CR36","unstructured":"Mao, X., Shen, C., & Yang, Y.B. (2016). Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Proceedings of the Annual Conference on Neural Information Processing Systems, pp. 2802\u20132810."},{"key":"2191_CR37","unstructured":"Mazzini, D. (2018). Guided upsampling network for real-time semantic segmentation. In: Proceedings of British Machine Vision Conference (BMVC), pp. 1\u201312."},{"issue":"6","key":"2191_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355089.3356528","volume":"38","author":"S Niklaus","year":"2019","unstructured":"Niklaus, S., Mai, L., Yang, J., & Liu, F. (2019). 3D ken burns effect from a single image. ACM Trans Graph, 38(6), 1\u201315.","journal-title":"ACM Trans Graph"},{"issue":"10","key":"2191_CR39","first-page":"e3","volume":"1","author":"A Odena","year":"2016","unstructured":"Odena, A., Dumoulin, V., & Olah, C. (2016). Deconvolution and checkerboard artifacts. Distill, 1(10), e3.","journal-title":"Deconvolution and checkerboard artifacts. Distill"},{"key":"2191_CR40","doi-asserted-by":"crossref","unstructured":"Peng, J., Cao, Z., Luo, X., Lu, H., Xian, K., & Zhang, J. (2022). BokehMe: When neural rendering meets classical rendering. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 16283\u201316292.","DOI":"10.1109\/CVPR52688.2022.01580"},{"key":"2191_CR41","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021). Learning transferable visual models from natural language supervision. Proc (pp. 8748\u20138763). PMLR: International Conference on Machine Learning"},{"key":"2191_CR42","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. Annual Conference on Neural Information Processing Systems 28."},{"key":"2191_CR43","doi-asserted-by":"crossref","unstructured":"Rhemann, C., Rother, C., Wang, J., Gelautz, M., Kohli, P., & Rott, P. (2009). A perceptually motivated online benchmark for image matting. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 1826\u20131833.","DOI":"10.1109\/CVPR.2009.5206503"},{"key":"2191_CR44","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2191_CR45","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2191_CR46","doi-asserted-by":"crossref","unstructured":"Shi, W., Caballero, J., Husz\u00e1r, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., & Wang, Z. (2016). Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 1874\u20131883.","DOI":"10.1109\/CVPR.2016.207"},{"key":"2191_CR47","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012). Indoor segmentation and support inference from RGBD images. In: Proceedings of the European Conference on Computer Vision, pp. 746\u2013760.","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"2191_CR48","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., & Xiao, J. (2015). SUN RGB-D: A RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 567\u2013576.","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"2191_CR49","doi-asserted-by":"crossref","unstructured":"Takikawa, T., Acuna, D., Jampani, V., & Fidler, S. (2019). Gated-scnn: Gated shape cnns for semantic segmentation. In: Proceedings of the IEEE conference on computer vision, pp. 5229\u20135238.","DOI":"10.1109\/ICCV.2019.00533"},{"key":"2191_CR50","first-page":"6105","volume":"97","author":"M Tan","year":"2019","unstructured":"Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, 97, 6105\u20136114.","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"2191_CR51","doi-asserted-by":"crossref","unstructured":"Tang, C., Chen, H., Li, X., Li, J., Zhang, Z., & Hu, X. (2021). Look closer to segment better: Boundary patch refinement for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 13926\u201313935.","DOI":"10.1109\/CVPR46437.2021.01371"},{"key":"2191_CR52","doi-asserted-by":"crossref","unstructured":"Teed, Z., & Deng, J. (2020). Raft: Recurrent all-pairs field transforms for optical flow. Proc (pp. 402\u2013419). European Conference on Computer Vision: Springer.","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"2191_CR53","doi-asserted-by":"crossref","unstructured":"Tian, Z., He, T., Shen, C., & Yan, Y. (2019). Decoders matter for semantic segmentation: Data-dependent decoding enables flexible feature aggregation. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 3126\u20133135.","DOI":"10.1109\/CVPR.2019.00324"},{"key":"2191_CR54","doi-asserted-by":"crossref","unstructured":"Tomasi, C., & Manduchi, R. (1998). Bilateral filtering for gray and color images. Proc (pp. 839\u2013846). IEEE International Conference on Computer Vision.","DOI":"10.1109\/ICCV.1998.710815"},{"key":"2191_CR55","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, K., Xu, R., Liu, Z., Loy, C.C., & Lin, D. (2019). CARAFE: Context-aware reassembly of features. In: Proc. IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3007\u20133016.","DOI":"10.1109\/ICCV.2019.00310"},{"issue":"10","key":"2191_CR56","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., et al. (2020). Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10), 3349\u20133364.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"9","key":"2191_CR57","first-page":"4674","volume":"44","author":"J Wang","year":"2021","unstructured":"Wang, J., Chen, K., Xu, R., Liu, Z., Loy, C. C., & Lin, D. (2021). CARAFE++: Unified Content-Aware ReAssembly of FEatures. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9), 4674\u20134687.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2191_CR58","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., & He, K. (2018). Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 7794\u20137803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2191_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3228927","volume":"60","author":"J Wu","year":"2022","unstructured":"Wu, J., Pan, Z., Lei, B., & Hu, Y. (2022). Fsanet: Feature-and-spatial-aligned network for tiny object detection in remote sensing images. Transactions on Geoscience and Remote Sensing, 60, 1\u201317.","journal-title":"Transactions on Geoscience and Remote Sensing"},{"key":"2191_CR60","doi-asserted-by":"crossref","unstructured":"Xian, K., Shen, C., Cao, Z., Lu, H., Xiao, Y., Li, R., & Luo, Z. (2018). Monocular relative depth perception with web stereo data supervision. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 311\u2013320.","DOI":"10.1109\/CVPR.2018.00040"},{"key":"2191_CR61","unstructured":"Xiao, H., Rasul, K., & Vollgraf, R. (2017), Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv Comput Res Repository."},{"key":"2191_CR62","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., & Sun, J. (2018). Unified perceptual parsing for scene understanding. In: Proceedings of the European Conference on Computer Vision, pp. 418\u2013434.","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"2191_CR63","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., & Luo, P. (2021). SegFormer: Simple and efficient design for semantic segmentation with transformers. In: Proceedings of the Annual Conference on Neural Information Processing Systems, pp. 12077\u201312090."},{"key":"2191_CR64","doi-asserted-by":"crossref","unstructured":"Xie, S., & Tu, Z. (2015). Holistically-nested edge detection. In: Proceedings of the European Conference on Computer Vision, pp. 1395\u20131403.","DOI":"10.1109\/ICCV.2015.164"},{"key":"2191_CR65","doi-asserted-by":"crossref","unstructured":"Xu, N., Price, B., Cohen, S., & Huang, T. (2017). Deep image matting. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 2970\u20132979.","DOI":"10.1109\/CVPR.2017.41"},{"issue":"8","key":"2191_CR66","doi-asserted-by":"publisher","first-page":"2375","DOI":"10.1007\/s11263-021-01465-9","volume":"129","author":"Y Yuan","year":"2021","unstructured":"Yuan, Y., Huang, L., Guo, J., Zhang, C., Chen, X., & Wang, J. (2021). Ocnet: Object context for semantic segmentation. International Journal of Computer Vision, 129(8), 2375\u20132398.","journal-title":"International Journal of Computer Vision"},{"key":"2191_CR67","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In: Proceedings of the European Conference on Computer Vision, pp. 818\u2013833.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"2191_CR68","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., & Beyer, L. (2022). Scaling vision transformers. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 12104\u201312113.","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"2191_CR69","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"key":"2191_CR70","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., & Torr, P.H., et al. (2021). Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 6881\u20136890","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"2191_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 2921\u20132929.","DOI":"10.1109\/CVPR.2016.319"},{"key":"2191_CR72","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017). Scene parsing through ade20k dataset. In: Proceedings of the IEEE conference on computer vision and pattern Recognition, pp. 633\u2013641.","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02191-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02191-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02191-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T06:08:41Z","timestamp":1736230121000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02191-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,22]]},"references-count":72,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["2191"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02191-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,22]]},"assertion":[{"value":"26 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}