{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:41:18Z","timestamp":1769748078294,"version":"3.49.0"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031925900","type":"print"},{"value":"9783031925917","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-92591-7_18","type":"book-chapter","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T07:25:00Z","timestamp":1747985100000},"page":"286-304","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Segmenting Object Affordances: Reproducibility and\u00a0Sensitivity to\u00a0Scale"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9001-5641","authenticated-orcid":false,"given":"Tommaso","family":"Apicella","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8227-8529","authenticated-orcid":false,"given":"Alessio","family":"Xompero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5748-3942","authenticated-orcid":false,"given":"Paolo","family":"Gastaldo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5086-7858","authenticated-orcid":false,"given":"Andrea","family":"Cavallaro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Apicella, T., Xompero, A., Ragusa, E., Berta, R., Cavallaro, A., Gastaldo, P.: Affordance segmentation of hand-occluded containers from exocentric images. In: IEEE International Conference Computer Vision Workshops (2023)","DOI":"10.1109\/ICCVW60793.2023.00204"},{"key":"18_CR2","unstructured":"Badrinarayanan, V., Handa, A., Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv:1505.07293v1 [cs.CV] (2015)"},{"key":"18_CR3","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I","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.) Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I, pp. 213\u2013229. Springer International Publishing, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Caselles-Dupr\u00e9, H., Garcia-Ortiz, M., Filliat, D.: Are standard object segmentation models sufficient for learning affordance segmentation? arXiv:2107.02095v1 [cs.LG] (2021)","DOI":"10.1109\/IJCNN52387.2021.9533683"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chen, D., Kong, D., Li, J., Wang, S., Yin, B.: Adosmnet: a novel visual affordance detection network with object shape mask guided feature encoders. Multimedia Tools and Applications, pp. 1\u201325 (2023)","DOI":"10.1007\/s11042-023-16898-2"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Chen, D., Kong, D., Li, J., Wang, S., Yin, B.: A survey of visual affordance recognition based on deep learning. IEEE Trans. Big Data 1\u201320 (2023)","DOI":"10.1109\/TBDATA.2023.3291558"},{"issue":"4","key":"18_CR7","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR8","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 Computer Vision Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"18_CR9","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural Inf. Process. Syst. 34, 17864\u201317875 (2021)"},{"key":"18_CR10","unstructured":"Christensen, A.D., Lehotsk\u1ef3, D., J\u00f8rgensen, M.W., Chrysostomou, D.: Learning to segment object affordances on synthetic data for task-oriented robotic handovers. In: British Machice Vision Conference (2022)"},{"issue":"2","key":"18_CR11","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1109\/LRA.2019.2894439","volume":"4","author":"F Chu","year":"2019","unstructured":"Chu, F., Xu, R., Vela, P.: Learning affordance segmentation for real-world robotic manipulation via synthetic images. IEEE Robotics Autom. Lett. 4(2), 1140\u20131147 (2019)","journal-title":"IEEE Robotics Autom. Lett."},{"key":"18_CR12","unstructured":"Cui, L., Chen, X., Zhao, H., Zhou, G., Zhu, Y.: Strap: Structured object affordance segmentation with point supervision. arXiv:2304.08492v1 [cs.CV] (2023)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: Conference Computer Vision Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Do, T., Nguyen, A., Reid, I.: AffordanceNet: an end-to-end deep learning approach for object affordance detection. In: IEEE International Conference Robotics Automation (2018)","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: Conference of Computer Vision Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"18_CR16","unstructured":"Gibson, J.J., Carmichael, L.: The senses considered as perceptual systems, vol.\u00a02. Houghton Mifflin Boston (1966)"},{"key":"18_CR17","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.neucom.2021.01.018","volume":"440","author":"Q Gu","year":"2021","unstructured":"Gu, Q., Su, J., Yuan, L.: Visual affordance detection using an efficient attention convolutional neural network. Neurocomputing 440, 36\u201344 (2021)","journal-title":"Neurocomputing"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Guo, A., et al.: Handal: a dataset of real-world manipulable object categories with pose annotations, affordances, and reconstructions. In: IEEE International Conference Intelligent Robot System (2023)","DOI":"10.1109\/IROS55552.2023.10341672"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Hampali, S., Rad, M., Oberweger, M., Lepetit, V.: Honnotate: a method for 3D annotation of hand and object poses. In: Conference Computing Vision Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Hassan, M., Ghosh, P., Tesch, J., Tzionas, D., Black, M.J.: Populating 3D scenes by learning human-scene interaction. In: Conference Computer Vision Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01447"},{"issue":"3","key":"18_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3446370","volume":"54","author":"M Hassanin","year":"2021","unstructured":"Hassanin, M., Khan, S., Tahtali, M.: Visual affordance and function understanding: a survey. ACM Comput. Surv. (CSUR) 54(3), 1\u201335 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Conference Computer Vision Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: IEEE International Confernece Computer Vis. (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Conference Computer Vision Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Hu, Y., Chen, Y., Li, X., Feng, J.: Dynamic feature fusion for semantic edge detection. In: International Joint Conference on Artificial Intelligence (2019)","DOI":"10.24963\/ijcai.2019\/110"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Hussain.S, S., Liu, L., Xu, W., Lu, C.: FPHA-Afford: a domain-specific benchmark dataset for occluded object affordance estimation in human-object-robot interaction. In: IEEE International Conference Image Processing (2020)","DOI":"10.1109\/ICIP40778.2020.9190733"},{"key":"18_CR27","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: International Conference on Machine Learning (2021)"},{"issue":"4","key":"18_CR28","doi-asserted-by":"publisher","first-page":"9826","DOI":"10.1109\/LRA.2022.3191231","volume":"7","author":"J Jiang","year":"2022","unstructured":"Jiang, J., Cao, G., Do, T., Luo, S.: A4t: hierarchical affordance detection for transparent objects depth reconstruction and manipulation. IEEE Robot. Autom. Lett. 7(4), 9826\u20139833 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Khalifa, Z., Shah, S.A.A.: A large scale multi-view RGBD visual affordance learning dataset. In: IEEE International Conference Image Processing (2023)","DOI":"10.1109\/ICIP49359.2023.10222906"},{"issue":"1","key":"18_CR30","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.cviu.2010.08.002","volume":"115","author":"H Kjellstr\u00f6m","year":"2011","unstructured":"Kjellstr\u00f6m, H., Romero, J., Kragi\u0107, D.: Visual object-action recognition: inferring object affordances from human demonstration. Comput. Vis. Image Understand. 115(1), 81\u201390 (2011)","journal-title":"Comput. Vis. Image Understand."},{"issue":"1\u20132","key":"18_CR31","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. Quart. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Quart."},{"key":"18_CR32","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representation (2019)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Margolin, R., Zelnik-Manor, L., Tal, A.: How to evaluate foreground maps? In: Conference Computing Vision Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.39"},{"key":"18_CR34","unstructured":"Minh, C.N.D., Gilani, S.Z., Islam, S.M.S., Suter, D.: Learning affordance segmentation: an investigative study. In: Digital Image Computing: Techniques and Applications (2020)"},{"key":"18_CR35","unstructured":"Morrison, D., Milan, A., Antonakos, E.: Uncertainty-aware instance segmentation using dropout sampling. In: Robotic Vision Probabilistic Object Detection Challenge (CVPR Workshop) (2019)"},{"key":"18_CR36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160606","volume-title":"Bayesian Deep Learning for Affordance Segmentation in Images","author":"L Mur-Labadia","year":"2023","unstructured":"Mur-Labadia, L., Martinez-Cantin, R., Guerrero, J.J.: Bayesian Deep Learning for Affordance Segmentation in Images. IEEE Int. Conf, Robotics Autom (2023)"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Myers, A., Teo, C.L., Ferm\u00fcller, C., Aloimonos, Y.: Affordance detection of tool parts from geometric features. In: IEEE International Conference Robotics Automation (2015)","DOI":"10.1109\/ICRA.2015.7139369"},{"issue":"5","key":"18_CR38","first-page":"1257","volume":"42","author":"N Nauata","year":"2019","unstructured":"Nauata, N., Hu, H., Zhou, G.T., Deng, Z., Liao, Z., Mori, G.: Structured label inference for visual understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(5), 1257\u20131271 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Kanoulas, D., Caldwell, D., Tsagarakis, N.: Detecting object affordances with convolutional neural networks. In: IEEE International Conference Intelligent Robot System (2016)","DOI":"10.1109\/IROS.2016.7759429"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Kanoulas, D., Caldwell, D., Tsagarakis, N.: Object-based affordances detection with convolutional neural networks and dense conditional random fields. In: IEEE International Conference Intelligent Robot System (2017)","DOI":"10.1109\/IROS.2017.8206484"},{"key":"18_CR41","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/j.neubiorev.2017.04.014","volume":"77","author":"F Osiurak","year":"2017","unstructured":"Osiurak, F., Rossetti, Y., Badets, A.: What is an affordance? 40 years later. Neurosci. Biobehav. Rev. 77, 403\u2013417 (2017)","journal-title":"Neurosci. Biobehav. Rev."},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Pang, Y., Xompero, A., Oh, C., Cavallaro, A.: Towards safe human-to-robot handovers of unknown containers. In: IEEE International Conference Robot Human Interactive Communication (2021)","DOI":"10.1109\/RO-MAN50785.2021.9515350"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: International Conference Medical Image Computing Computer Assisted Intervention (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"1","key":"18_CR44","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1109\/LRA.2020.3026970","volume":"6","author":"P Rosenberger","year":"2020","unstructured":"Rosenberger, P., et al.: Object-independent human-to-robot handovers using real time robotic vision. IEEE Robot. Autom. Lett. 6(1), 17\u201323 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"2","key":"18_CR45","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.1109\/LRA.2020.2969200","volume":"5","author":"R Sanchez-Matilla","year":"2020","unstructured":"Sanchez-Matilla, R., et al.: Benchmark for human-to-robot handovers of unseen containers with unknown filling. IEEE Robot. Autom. Lett. 5(2), 1642\u20131649 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Sawatzky, J., Srikantha, A., Gall, J.: Weakly supervised affordance detection. In: Conference Computer Vision Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.552"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representation (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: IEEE International Conference Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Conference Computer Vision Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"18_CR50","doi-asserted-by":"crossref","unstructured":"Tang, M., Perazzi, F., Djelouah, A., Ben\u00a0Ayed, I., Schroers, C., Boykov, Y.: On regularized losses for weakly-supervised CNN segmentation. In: European Conference Computer Vision (2018)","DOI":"10.1007\/978-3-030-01270-0_31"},{"key":"18_CR51","doi-asserted-by":"crossref","unstructured":"Thakur, S., Beyan, C., Morerio, P., Murino, V., Del\u00a0Bue, A.: Leveraging next-active objects for context-aware anticipation in egocentric videos. In: WACV (2024)","DOI":"10.1109\/WACV57701.2024.00846"},{"key":"18_CR52","unstructured":"Weber, X., Xompero, A., Cavallaro, A.: A mixed-reality dataset for category-level 6D pose and size estimation of hand-occluded containers. arXiv:2211.10470v1 [cs.CV] (2022)"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Wen, B., et al.: Bundlesdf: Neural 6-dof tracking and 3d reconstruction of unknown objects. In: Conference Computer Vision Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00066"},{"key":"18_CR54","unstructured":"Wu, H., Zhang, J., Huang, K., Liang, K., Yu, Y.: FastFCN: rethinking dilated convolution in the backbone for semantic segmentation. arXiv:1903.11816v1 [cs.CV] (2019)"},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Conference Computer Vision Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"18_CR56","doi-asserted-by":"publisher","first-page":"41388","DOI":"10.1109\/ACCESS.2022.3166906","volume":"10","author":"A Xompero","year":"2022","unstructured":"Xompero, A., et al.: The CORSMAL benchmark for the prediction of the properties of containers. IEEE Access 10, 41388\u201341402 (2022)","journal-title":"IEEE Access"},{"key":"18_CR57","unstructured":"Xompero, A., Sanchez-Matilla, R., Mazzon, R., Cavallaro, A.: CORSMAL Containers Manipulation (2020). https:\/\/doi.org\/10.17636\/101CORSMAL1, (1.0) [Data set]. Queen Mary University of London"},{"key":"18_CR58","doi-asserted-by":"crossref","unstructured":"Yang, W., Paxton, C., Mousavian, A., Chao, Y., Cakmak, M., Fox, D.: Reactive human-to-robot handovers of arbitrary objects. In: IEEE International Conference Robotics Automation (2021)","DOI":"10.1109\/ICRA48506.2021.9561170"},{"issue":"20","key":"18_CR59","doi-asserted-by":"publisher","first-page":"17963","DOI":"10.1007\/s00521-022-07446-4","volume":"34","author":"C Yin","year":"2022","unstructured":"Yin, C., Zhang, Q.: Object affordance detection with boundary-preserving network for robotic manipulation tasks. Neural Comput. Appl. 34(20), 17963\u201317980 (2022)","journal-title":"Neural Comput. Appl."},{"issue":"1","key":"18_CR60","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10846-021-01525-9","volume":"104","author":"C Yin","year":"2022","unstructured":"Yin, C., Zhang, Q., Ren, W.: A new semantic edge aware network for object affordance detection. J. Intell. Robot. Syst. 104(1), 1\u201316 (2022)","journal-title":"J. Intell. Robot. Syst."},{"key":"18_CR61","doi-asserted-by":"crossref","unstructured":"Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 472\u2013480 (2017)","DOI":"10.1109\/CVPR.2017.75"},{"key":"18_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Context encoding for semantic segmentation. In: Conference Computer Vision Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00388"},{"key":"18_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, H., et\u00a0al.: Resnest: split-attention networks. In: Conference Computer Vision Pattern Recognition (2022)","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"18_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xue, J., Dana, K.: Deep ten: Texture encoding network. In: Conference Computer Vision Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.309"},{"key":"18_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, H., Ren, T., Dou, Y., Li, Q.: Multi-scale fusion and global semantic encoding for affordance detection. In: International Joint Conference on Neural Networks (2022)","DOI":"10.1109\/IJCNN55064.2022.9892363"},{"key":"18_CR66","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Conference Computer Vision Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"issue":"18","key":"18_CR67","doi-asserted-by":"publisher","first-page":"14321","DOI":"10.1007\/s00521-019-04336-0","volume":"32","author":"X Zhao","year":"2020","unstructured":"Zhao, X., Cao, Y., Kang, Y.: Object affordance detection with relationship-aware network. Neural Comput. Appl. 32(18), 14321\u201314333 (2020)","journal-title":"Neural Comput. Appl."},{"key":"18_CR68","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92591-7_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T07:25:42Z","timestamp":1747985142000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92591-7_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031925900","9783031925917"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92591-7_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}