{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T04:23:00Z","timestamp":1787372580368,"version":"build-2736575974"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"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 Foundation of China","doi-asserted-by":"publisher","award":["National Natural"],"award-info":[{"award-number":["National Natural"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s11263-026-02950-9","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T08:56:35Z","timestamp":1784710595000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual-Geometric Collaborative Guidance for Affordance Learning"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0744-2074","authenticated-orcid":false,"given":"Hongchen","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"2950_CR1","unstructured":"Bai, S., Kolter, J. Z., & Koltun, V. (2019). Deep equilibrium models. Advances in neural information processing systems (32)."},{"key":"2950_CR2","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B. L., Xie, X., Petrov, I. A., Sminchisescu, C., Theobalt, C., & Pons-Moll, G. (2022). Behave: Dataset and method for tracking human object interactions. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (15935\u201315946).","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"2950_CR3","unstructured":"Bylinskii, Z., Judd, T., Borji, A., Itti, L., Durand, F., Oliva, A., & Torralba, A. (2015). Mit saliency benchmark."},{"issue":"3","key":"2950_CR4","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/TPAMI.2018.2815601","volume":"41","author":"Z Bylinskii","year":"2018","unstructured":"Bylinskii, Z., Judd, T., Oliva, A., Torralba, A., & Durand, F. (2018). What do different evaluation metrics tell us about saliency models? IEEE transactions on pattern analysis and machine intelligence, 41(3), 740\u2013757.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2950_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Z., Yin, W., Zeng, A., Wei, C., Sun, Q., Yanjun, W., Pang, H.E., Mei, H., Zhang, M., & Zhang, L and others. (2024) Smpler-x: Scaling up expressive human pose and shape estimation. Advances in Neural Information Processing Systems 36.","DOI":"10.52202\/075280-0506"},{"key":"2950_CR6","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H. & Deng, J. (2018). Learning to detect human-object interactions. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, 381\u2013389.","DOI":"10.1109\/WACV.2018.00048"},{"key":"2950_CR7","doi-asserted-by":"crossref","unstructured":"Chen, C., Seff, A., Kornhauser, A., & Xiao, J. (2015). Deepdriving: Learning affordance for direct perception in autonomous driving. Proceedings of the IEEE international conference on computer vision (2722\u20132730).","DOI":"10.1109\/ICCV.2015.312"},{"key":"2950_CR8","doi-asserted-by":"crossref","unstructured":"Chen, J., Gao, D., Lin, K.Q., Shou, M.Z. (2023a). Affordance grounding from demonstration video to target image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6799\u20136808.","DOI":"10.1109\/CVPR52729.2023.00657"},{"key":"2950_CR9","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. Proceedings of the European conference on computer vision (ECCV) (801\u2013818).","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2950_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dwivedi, S.K., Black, M.J. & Tzionas, D. (2023b). Detecting human-object contact in images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 17100\u201317110.","DOI":"10.1109\/CVPR52729.2023.01640"},{"key":"2950_CR11","doi-asserted-by":"crossref","unstructured":"Chuang, C. Y., Li, J., Torralba, A., & Fidler, S. (2018). Learning to act properly: Predicting and explaining affordances from images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (975\u2013983).","DOI":"10.1109\/CVPR.2018.00108"},{"key":"2950_CR12","doi-asserted-by":"crossref","unstructured":"Cseke, A., Tripathi, S., Dwivedi, S. K., Lakshmipathy, A. S., Chatterjee, A., Black, M. J., & Tzionas, D. (2025). Pico: Reconstructing 3d people in contact with objects. Proceedings of the Computer Vision and Pattern Recognition Conference (1783\u20131794).","DOI":"10.1109\/CVPR52734.2025.00173"},{"key":"2950_CR13","doi-asserted-by":"crossref","unstructured":"Deng, S., Xu, X., Wu, C., Chen, K., & Jia, K.2021) 3d affordancenet: A benchmark for visual object affordance understanding. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (1778\u20131787).","DOI":"10.1109\/CVPR46437.2021.00182"},{"key":"2950_CR14","doi-asserted-by":"crossref","unstructured":"Do, T. T., Nguyen, A., & Reid, I. (2018). Affordancenet: An end-to-end deep learning approach for object affordance detection. IEEE international conference on robotics and automation (ICRA), 5882\u20135889. IEEE.","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"2950_CR15","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. International Conference on Learning Representations."},{"key":"2950_CR16","doi-asserted-by":"crossref","unstructured":"Dwivedi, S. K., Anti\u0107, D., Tripathi, S., Taheri, O., Schmid, C., Black, M. J., & Tzionas, D. (2025). Interactvlm: 3d interaction reasoning from 2d foundational models. Proceedings of the Computer Vision and Pattern Recognition Conference (22605\u201322615).","DOI":"10.1109\/CVPR52734.2025.02105"},{"key":"2950_CR17","doi-asserted-by":"crossref","unstructured":"Fang, K., Wu, T.L., Yang, D., Savarese, S. & Lim, J.J. (2018). Demo2vec: Reasoning object affordances from online videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2139\u20132147.","DOI":"10.1109\/CVPR.2018.00228"},{"issue":"12","key":"2950_CR18","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1145\/3458723","volume":"64","author":"T Gebru","year":"2021","unstructured":"Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., Iii, H. D., & Crawford, K. (2021). Datasheets for datasets. Communications of the ACM, 64(12), 86\u201392.","journal-title":"Communications of the ACM"},{"issue":"2","key":"2950_CR19","first-page":"67","volume":"1","author":"JJ Gibson","year":"1977","unstructured":"Gibson, J. J. (1977). The theory of affordances. Hilldale, USA, 1(2), 67\u201382.","journal-title":"Hilldale, USA"},{"key":"2950_CR20","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., & He, K. (2018). Detecting and recognizing human-object interactions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00872"},{"key":"2950_CR21","unstructured":"Grauman, K., Westbury, A., Byrne, E., Chavis, Z., Furnari, A., Girdhar, R., Hamburger, J., Jiang, H., Liu, M., Liu, X. and others. (2022). Ego4d: Around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 18995\u201319012."},{"issue":"3","key":"2950_CR22","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. (2021). Visual affordance and function understanding: A survey. ACM Computing Surveys (CSUR), 54(3), 1\u201335.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2950_CR23","unstructured":"Huang, H., Luo, H., Zhai, W., Cao, Y., & Zha, Z. J. (2024). Leverage task context for object affordance ranking. arXiv preprint, arXiv:2411.16082."},{"key":"2950_CR24","unstructured":"Judd, T., Durand, F., & Torralba, A. (2012). A benchmark of computational models of saliency to predict human fixations."},{"key":"2950_CR25","doi-asserted-by":"crossref","unstructured":"Kim, B., Lee, J., Kang, J., Kim, E.S. & Kim, H.J. (2021). Hotr: End-to-end human-object interaction detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 74\u201383.","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"2950_CR26","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L. J., Shamma, D. A., et al. (2017). Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision, 123, 32\u201373.","journal-title":"International journal of computer vision"},{"key":"2950_CR27","doi-asserted-by":"crossref","unstructured":"Li, G., Jampani, V., Sun, D., & Sevilla-Lara, L. (2023). Locate: Localize and transfer object parts for weakly supervised affordance grounding. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 10922\u201310931)","DOI":"10.1109\/CVPR52729.2023.01051"},{"key":"2950_CR28","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 (ECCV), Springer, 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2950_CR29","unstructured":"Loshchilov, I., & Hutter, F. (2017). arXiv:1711.05101 Decoupled weight decay regularization. arXiv preprint."},{"key":"2950_CR30","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y., & Tao, D. (2021). arXiv:2106.14747 One-shot affordance detection. arXiv preprint.","DOI":"10.24963\/ijcai.2021\/124"},{"key":"2950_CR31","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y., & Tao, D. (2022). Learning affordance grounding from exocentric images. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2252\u20132261)","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"2950_CR32","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y., & Tao, D. (2023). Leverage interactive affinity for affordance learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 6809\u20136819)","DOI":"10.1109\/CVPR52729.2023.00658"},{"key":"2950_CR33","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., Hartley, R., & Salzmann, M. (2022). Contact-aware human motion forecasting arXiv:2210.03954 arXiv preprint.","DOI":"10.52202\/068431-0534"},{"key":"2950_CR34","doi-asserted-by":"crossref","unstructured":"Min, J., Kang, D., & Cho, M. (2021). Hypercorrelation squeeze for few-shot segmentation. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"2950_CR35","doi-asserted-by":"crossref","unstructured":"Moon, W., Seong, H. S., & Heo, J. P. (2025). Selective contrastive learning for weakly supervised affordance grounding. Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 5210\u20135220)","DOI":"10.1109\/ICCV51701.2025.00495"},{"key":"2950_CR36","doi-asserted-by":"crossref","unstructured":"Myers, A., Teo, C. L., Ferm\u00fcller, C., & Aloimonos, Y. (2015). Affordance detection of tool parts from geometric features. 2015 IEEE International Conference on Robotics and Automation (ICRA) (pp. 1374\u20131381). IEEE.","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"2950_CR37","first-page":"2005","volume":"33","author":"T Nagarajan","year":"2020","unstructured":"Nagarajan, T., & Grauman, K. (2020). Learning affordance landscapes for interaction exploration in 3d environments. Advances in Neural Information Processing Systems, 33, 2005\u20132015.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2950_CR38","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Feichtenhofer, C., & Grauman, K. (2019). Grounded human-object interaction hotspots from video. Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 8688\u20138697)","DOI":"10.1109\/ICCV.2019.00878"},{"key":"2950_CR39","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Kanoulas, D., Caldwell, D. G., & Tsagarakis, N. G. (2016). Detecting object affordances with convolutional neural networks. IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 2765\u20132770). IEEE.","DOI":"10.1109\/IROS.2016.7759429"},{"key":"2950_CR40","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Kanoulas, D., Caldwell, D. G., & Tsagarakis, N. G. (2017). Object-based affordances detection with convolutional neural networks and dense conditional random fields. IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 5908\u20135915). IEEE.","DOI":"10.1109\/IROS.2017.8206484"},{"issue":"18","key":"2950_CR41","doi-asserted-by":"publisher","first-page":"2397","DOI":"10.1016\/j.visres.2005.03.019","volume":"45","author":"RJ Peters","year":"2005","unstructured":"Peters, R. J., Iyer, A., Itti, L., & Koch, C. (2005). Components of bottom-up gaze allocation in natural images. Vision research, 45(18), 2397\u20132416.","journal-title":"Vision research"},{"key":"2950_CR42","doi-asserted-by":"crossref","unstructured":"Qi, S., Huang, S., Wei, P., & Zhu, S. C. (2017). Predicting human activities using stochastic grammar. Proceedings of the IEEE International Conference on Computer Vision (pp. 1164\u20131172)","DOI":"10.1109\/ICCV.2017.132"},{"key":"2950_CR43","doi-asserted-by":"publisher","first-page":"43041","DOI":"10.52202\/075280-1865","volume":"36","author":"M Qu","year":"2023","unstructured":"Qu, M., Wu, Y., Liu, W., Liang, X., Song, J., Zhao, Y., & Wei, Y. (2023). Rio: A benchmark for reasoning intention-oriented objects in open environments. Advances in Neural Information Processing Systems, 36, 43041\u201343056.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2950_CR44","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Goh, R. A., Agarwal, G., Sastry, S., Askell, G., Mishkin, A., Clark, P., & J. (2021). Learning transferable visual models from natural language supervision. International conference on machine learning (pp. 8748\u20138763) PMLR."},{"key":"2950_CR45","doi-asserted-by":"crossref","unstructured":"Sawatzky, J., & Gall, J. (2017). Adaptive binarization for weakly supervised affordance segmentation. Proceedings of the IEEE International Conference on Computer Vision Workshops (pp. 1383\u20131391)","DOI":"10.1109\/ICCVW.2017.164"},{"key":"2950_CR46","doi-asserted-by":"crossref","unstructured":"Sawatzky, J., Srikantha, A., & Gall, J. (2017). Weakly supervised affordance detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2795\u20132804)","DOI":"10.1109\/CVPR.2017.552"},{"key":"2950_CR47","doi-asserted-by":"crossref","unstructured":"Shao, Y., Zhai, W., Yang, Y., Luo, H., Cao, Y., & Zha, Z. J. (2025). Great: Geometry-intention collaborative inference for open-vocabulary 3d object affordance grounding. Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 17326\u201317336)","DOI":"10.1109\/CVPR52734.2025.01615"},{"key":"2950_CR48","doi-asserted-by":"crossref","unstructured":"Shimada, S., Golyanik, V., Li, Z., P\u00e9rez, P., Xu, W., & Theobalt, C. (2022). Hulc: 3d human motion capture with pose manifold sampling and dense contact guidance. European Conference on Computer Vision (pp. 516\u2013533). Springer.","DOI":"10.1007\/978-3-031-20047-2_30"},{"key":"2950_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2021.102359","volume":"60","author":"Y Sun","year":"2021","unstructured":"Sun, Y., Fang, S., & Zhang, Z. J. (2021). Impression management strategies on enterprise social media platforms: An affordance perspective. International Journal of Information Management, 60, Article 102359.","journal-title":"International Journal of Information Management"},{"issue":"1","key":"2950_CR50","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/BF00130487","volume":"7","author":"MJ Swain","year":"1991","unstructured":"Swain, M. J., & Ballard, D. H. (1991). Color indexing. International Journal of Computer Vision (IJCV), 7(1), 11\u201332.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"2950_CR51","doi-asserted-by":"crossref","unstructured":"Tang, J., Zheng, G., Yu, J., & Yang, S. (2023). Cotdet: Affordance knowledge prompting for task driven object detection. Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 3068\u20133078)","DOI":"10.1109\/ICCV51070.2023.00285"},{"key":"2950_CR52","doi-asserted-by":"crossref","unstructured":"Tang, J., Wei, Z., Zheng, G. & Yang, S. (2025a). Closed-loop transfer for weakly-supervised affordance grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9530\u20139539.","DOI":"10.1109\/ICCV51701.2025.00889"},{"key":"2950_CR53","doi-asserted-by":"crossref","unstructured":"Tang, Y., Huang, W., Wang, Y., Li, C., Yuan, R., Zhang, R., Wu, J. & Fei-Fei, L. (2025b). Uad: Unsupervised affordance distillation for generalization in robotic manipulation. arXiv preprint arXiv:2506.09284.","DOI":"10.1109\/ICRA55743.2025.11128868"},{"key":"2950_CR54","doi-asserted-by":"crossref","unstructured":"Tripathi, S., Chatterjee, A., Passy, J.C., Yi, H., Tzionas, D. & Black, M.J. (2023). Deco: Dense estimation of 3d human-scene contact in the wild. In: Proceedings of the IEEE\/CVF international conference on computer vision, 8001\u20138013.","DOI":"10.1109\/ICCV51070.2023.00735"},{"key":"2950_CR55","unstructured":"Turc, I., Chang, M. W., Lee, K., & Toutanova, K. (2019). Well-read students learn better: On the importance of pre-training compact models arXiv preprint, arXiv:1908.08962v2."},{"key":"2950_CR56","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141. & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems 30."},{"key":"2950_CR57","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhang, S., Sun, F., Chen, W. & Wu, P. (2025a). Affordstruct: Weakly supervised affordance grounding based on spatial interaction and knowledge-aware. IEEE Transactions on Automation Science and Engineering.","DOI":"10.1109\/TASE.2025.3586983"},{"key":"2950_CR58","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lei, Y., Wei, Z., Xue, W., Jiang, X., Zhuang, N. & Liu, Q. (2025b). Prompt guidance and human proximal perception for hot prediction with regional joint loss. arXiv preprint arXiv:2507.01630","DOI":"10.1109\/ICCV51701.2025.02194"},{"key":"2950_CR59","doi-asserted-by":"publisher","first-page":"8187","DOI":"10.1609\/aaai.v39i8.32883","volume":"39","author":"Y Wang","year":"2025","unstructured":"Wang, Y., Neng, W., Wei, Z., Lei, Y., Xue, W., Zhuang, N., Xu, Y., Jiang, X., & Liu, Q. (2025). Precision-enhanced human-object contact detection via depth-aware perspective interaction and object texture restoration. Proceedings of the AAAI Conference on Artificial Intelligence, 39, 8187\u20138195.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2950_CR60","first-page":"12077","volume":"34","author":"E Xie","year":"2021","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. Advances in Neural Information Processing Systems, 34, 12077\u201312090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2950_CR61","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhang, J., Zhang, Q. & Tao, D. (2022). ViTPose: Simple vision transformer baselines for human pose estimation. In: Advances in Neural Information Processing Systems.","DOI":"10.52202\/068431-2795"},{"key":"2950_CR62","doi-asserted-by":"crossref","unstructured":"Yalandur\u00a0Muralidhar,P., Xue, Y., Xie, X., Kostyrko, M. & Pons-Moll, G. (2025). Physic: Physically plausible 3d human-scene interaction and contact from a single image.","DOI":"10.1145\/3757377.3763862"},{"key":"2950_CR63","doi-asserted-by":"crossref","unstructured":"Yamanobe, N., Wan, W., Ramirez-Alpizar, I. G., Petit, D., Tsuji, T., Akizuki, S., Hashimoto, M., Nagata, K., & Harada, K. (2017). A brief review of affordance in robotic manipulation research. Advanced Robotics,31(19\u201320), 1086\u20131101.","DOI":"10.1080\/01691864.2017.1394912"},{"key":"2950_CR64","doi-asserted-by":"crossref","unstructured":"Yang, F., Chen, W., Yang, K., Lin, H., Luo, D., Tang, C., Li, Z. & Wang, Y. (2025). Learning granularity-aware affordances from human-object interaction for tool-based functional dexterous grasping. IEEE Transactions on Neural Networks and Learning Systems.","DOI":"10.1109\/TNNLS.2025.3591538"},{"key":"2950_CR65","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhan, X., Li, K., Xu, W., Li, J. & Lu, C. (2021). Cpf: Learning a contact potential field to model the hand-object interaction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 11097\u201311106.","DOI":"10.1109\/ICCV48922.2021.01091"},{"key":"2950_CR66","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhai, W., Luo, H., Cao, Y., Luo, J. & Zha, Z.J. (2023). Grounding 3d object affordance from 2d interactions in images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 10905\u201310915.","DOI":"10.1109\/ICCV51070.2023.01001"},{"key":"2950_CR67","unstructured":"Yuan, Y., Fu, R., Huang, L., Lin, W., Zhang, C., Chen, X., & Wang, J. (2021). Hrformer: High-resolution transformer for dense prediction. NeurIPS."},{"issue":"10","key":"2950_CR68","doi-asserted-by":"publisher","first-page":"2472","DOI":"10.1007\/s11263-022-01642-4","volume":"130","author":"W Zhai","year":"2022","unstructured":"Zhai, W., Luo, H., Zhang, J., Cao, Y., & Tao, D. (2022). One-shot object affordance detection in the wild. International Journal of Computer Vision, 130(10), 2472\u20132500.","journal-title":"International Journal of Computer Vision"},{"key":"2950_CR69","doi-asserted-by":"crossref","unstructured":"Zhang Z, Luo H, Zhai W, Cao Y, Kang Y (2024a) Bidirectional progressive transformer for interaction intention anticipation. arXiv preprint arXiv:2405.05552","DOI":"10.1007\/978-3-031-73202-7_4"},{"key":"2950_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Luo, H., Zhai, W., Cao, Y. & Kang, Y. (2024b). Pear: Phrase-based hand-object interaction anticipation. arXiv preprint arXiv:2407.21510","DOI":"10.1007\/s11432-024-4405-4"},{"key":"2950_CR71","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2881\u20132890)","DOI":"10.1109\/CVPR.2017.660"},{"issue":"18","key":"2950_CR72","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. (2020). Object affordance detection with relationship-aware network. Neural Computing and Applications, 32(18), 14321\u201314333.","journal-title":"Neural Computing and Applications"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02950-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02950-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02950-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T03:23:07Z","timestamp":1787368987000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02950-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":72,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["2950"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02950-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]},"assertion":[{"value":"28 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","label":"Ethical Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":3,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":4,"name":"Ethics","label":"Conflicts of Interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"357"}}