{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T17:53:08Z","timestamp":1776275588989,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"name":"National Key R&D Program of China","award":["2021ZD0111601"],"award-info":[{"award-number":["2021ZD0111601"]}]},{"name":"National Natural Science Foundation of China","award":["62436009"],"award-info":[{"award-number":["62436009"]}]},{"name":"Natural Science Foundation of China","award":["62002395"],"award-info":[{"award-number":["62002395"]}]},{"name":"Natural Science Foundation of China","award":["6232260"],"award-info":[{"award-number":["6232260"]}]},{"name":"open research fund of Pengcheng Laboratory","award":["2025KF1B0050"],"award-info":[{"award-number":["2025KF1B0050"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2025A1515011874"],"award-info":[{"award-number":["2025A1515011874"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754778","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:27:39Z","timestamp":1761377259000},"page":"2821-2830","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7822-8041","authenticated-orcid":false,"given":"Zeming","family":"Wei","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0256-0345","authenticated-orcid":false,"given":"Junyi","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9423-9252","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8081-1289","authenticated-orcid":false,"given":"Weixing","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, GuangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7731-6746","authenticated-orcid":false,"given":"Jingzhou","family":"Luo","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2486-2890","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China, Peng Cheng Laboratory, Shenzhen, China, and Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China, Peng Cheng Laboratory, Shenzhen, China, and Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"e_1_3_2_2_2_1","volume-title":"Alison Bartsch, Abraham George, and Amir Barati Farimani.","author":"Car Arvind","year":"2024","unstructured":"Arvind Car, Sai Sravan Yarlagadda, Alison Bartsch, Abraham George, and Amir Barati Farimani. 2024. PLATO: Planning with LLMs and Affordances for Tool Manipulation. arXiv preprint arXiv:2409.11580 (2024)."},{"key":"e_1_3_2_2_3_1","volume-title":"Segment any 3d gaussians. arXiv preprint arXiv:2312.00860","author":"Cen Jiazhong","year":"2023","unstructured":"Jiazhong Cen, Jiemin Fang, Chen Yang, Lingxi Xie, Xiaopeng Zhang, Wei Shen, and Qi Tian. 2023a. Segment any 3d gaussians. arXiv preprint arXiv:2312.00860 (2023)."},{"key":"e_1_3_2_2_4_1","volume-title":"Segment any 3d gaussians. arXiv preprint arXiv:2312.00860","author":"Cen Jiazhong","year":"2023","unstructured":"Jiazhong Cen, Jiemin Fang, Chen Yang, Lingxi Xie, Xiaopeng Zhang, Wei Shen, and Qi Tian. 2023b. Segment any 3d gaussians. arXiv preprint arXiv:2312.00860 (2023)."},{"key":"e_1_3_2_2_5_1","volume-title":"European Conference on Computer Vision. Springer, 289-305","author":"Choi Seokhun","year":"2024","unstructured":"Seokhun Choi, Hyeonseop Song, Jaechul Kim, Taehyeong Kim, and Hoseok Do. 2024. Click-gaussian: Interactive segmentation to any 3d gaussians. In European Conference on Computer Vision. Springer, 289-305."},{"key":"e_1_3_2_2_6_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Chu Hengshuo","year":"2025","unstructured":"Hengshuo Chu, Xiang Deng, Qi Lv, Xiaoyang Chen, Yinchuan Li, Jianye HAO, and Liqiang Nie. 2025. 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_2_7_1","volume-title":"IRIS: Interactive Responsive Intelligent Segmentation for 3D Affordance Analysis. arXiv e-prints","author":"Chu Meng","year":"2024","unstructured":"Meng Chu and Xuan Zhang. 2024. IRIS: Interactive Responsive Intelligent Segmentation for 3D Affordance Analysis. arXiv e-prints (2024), arXiv-2409."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00182"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"e_1_3_2_2_11_1","volume-title":"Learning 2d invariant affordance knowledge for 3d affordance grounding. arXiv preprint arXiv:2408.13024","author":"Gao Xianqiang","year":"2024","unstructured":"Xianqiang Gao, Pingrui Zhang, Delin Qu, Dong Wang, Zhigang Wang, Yan Ding, Bin Zhao, and Xuelong Li. 2024. Learning 2d invariant affordance knowledge for 3d affordance grounding. arXiv preprint arXiv:2408.13024 (2024)."},{"key":"e_1_3_2_2_12_1","volume-title":"The theory of affordances. Perceiving, acting, and knowing: toward an ecological psychology. Perceiving, Acting, and Knowing: Toward an Ecological Psychology","author":"Gibson James J","year":"1977","unstructured":"James J Gibson. 1977. The theory of affordances. Perceiving, acting, and knowing: toward an ecological psychology. Perceiving, Acting, and Knowing: Toward an Ecological Psychology (1977), 67-82."},{"key":"e_1_3_2_2_13_1","volume-title":"2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos. arXiv preprint arXiv:2503.09320","author":"Heidinger Marvin","year":"2025","unstructured":"Marvin Heidinger, Snehal Jauhri, Vignesh Prasad, and Georgia Chalvatzaki. 2025. 2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos. arXiv preprint arXiv:2503.09320 (2025)."},{"key":"e_1_3_2_2_14_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_2_15_1","volume-title":"SAGD: Boundary-enhanced segment anything in 3D Gaussian via Gaussian decomposition. arXiv preprint arXiv:2401.17857","author":"Hu Xu","year":"2024","unstructured":"Xu Hu, Yuxi Wang, Lue Fan, Junsong Fan, Junran Peng, Zhen Lei, Qing Li, and Zhaoxiang Zhang. 2024. SAGD: Boundary-enhanced segment anything in 3D Gaussian via Gaussian decomposition. arXiv preprint arXiv:2401.17857 (2024)."},{"key":"e_1_3_2_2_16_1","volume-title":"INTRA: Interaction Relationship-Aware Weakly Supervised Affordance Grounding. In European Conference on Computer Vision. Springer, 18-34","author":"Jang Ji Ha","year":"2024","unstructured":"Ji Ha Jang, Hoigi Seo, and Se Young Chun. 2024. INTRA: Interaction Relationship-Aware Weakly Supervised Affordance Grounding. In European Conference on Computer Vision. Springer, 18-34."},{"key":"e_1_3_2_2_17_1","volume-title":"Conference on Robot Learning","volume":"1460","author":"Ji Mazeyu","year":"2024","unstructured":"Mazeyu Ji, Ri-Zhao Qiu, Xueyan Zou, and Xiaolong Wang. 2024. GraspSplats: Efficient Manipulation with 3D Feature Splatting. In Conference on Robot Learning, 6-9 November 2024, Munich, Germany (Proceedings of Machine Learning Research, Vol. 270), Pulkit Agrawal, Oliver Kroemer, and Wolfram Burgard (Eds.). PMLR, 1443-1460."},{"key":"e_1_3_2_2_18_1","volume-title":"CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting. arXiv preprint arXiv:2412.19142","author":"Jiao Siyu","year":"2024","unstructured":"Siyu Jiao, Haoye Dong, Yuyang Yin, Zequn Jie, Yinlong Qian, Yao Zhao, Humphrey Shi, and Yunchao Wei. 2024. CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting. arXiv preprint arXiv:2412.19142 (2024)."},{"key":"e_1_3_2_2_19_1","volume-title":"Gradient-Driven 3D Segmentation and Affordance Transfer in Gaussian Splatting Using 2D Masks. arXiv preprint arXiv:2409.11681","author":"Joseph Joji","year":"2024","unstructured":"Joji Joseph, Bharadwaj Amrutur, and Shalabh Bhatnagar. 2024. Gradient-Driven 3D Segmentation and Affordance Transfer in Gaussian Splatting Using 2D Masks. arXiv preprint arXiv:2409.11681 (2024)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01051"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00298"},{"key":"e_1_3_2_2_24_1","volume-title":"4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models. arXiv preprint arXiv:2503.10437","author":"Li Wanhua","year":"2025","unstructured":"Wanhua Li, Renping Zhou, Jiawei Zhou, Yingwei Song, Johannes Herter, Minghan Qin, Gao Huang, and Hanspeter Pfister. 2025. 4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models. arXiv preprint arXiv:2503.10437 (2025)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01351"},{"key":"e_1_3_2_2_26_1","volume-title":"Aligning cyber space with physical world: A comprehensive survey on embodied ai. arXiv preprint arXiv:2407.06886","author":"Liu Yang","year":"2024","unstructured":"Yang Liu, Weixing Chen, Yongjie Bai, Xiaodan Liang, Guanbin Li, Wen Gao, and Liang Lin. 2024. Aligning cyber space with physical world: A comprehensive survey on embodied ai. arXiv preprint arXiv:2407.06886 (2024)."},{"key":"e_1_3_2_2_27_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00489"},{"key":"e_1_3_2_2_29_1","volume-title":"AUC: a misleading measure of the performance of predictive distribution models. Global ecology and Biogeography","author":"Lobo Jorge M","year":"2008","unstructured":"Jorge M Lobo, Alberto Jim\u00e9nez-Valverde, and Raimundo Real. 2008. AUC: a misleading measure of the performance of predictive distribution models. Global ecology and Biogeography, Vol. 17, 2 (2008), 145-151."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00164"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"e_1_3_2_2_33_1","volume-title":"Luc Van Gool, and Danda Pani Paudel","author":"Ma Qi","year":"2024","unstructured":"Qi Ma, Yue Li, Bin Ren, Nicu Sebe, Ender Konukoglu, Theo Gevers, Luc Van Gool, and Danda Pani Paudel. 2024. Shapesplat: A large-scale dataset of gaussian splats and their self-supervised pretraining. arXiv preprint arXiv:2408.10906 (2024)."},{"key":"e_1_3_2_2_34_1","volume-title":"1st Workshop on X-Embodiment Robot Learning.","author":"Nasiriany Soroush","year":"2024","unstructured":"Soroush Nasiriany, Sean Kirmani, Tianli Ding, Laura Smith, Yuke Zhu, Danny Driess, Dorsa Sadigh, and Ted Xiao. 2024. RT-Affordance: Affordances are Versatile Intermediate Representations for Robot Manipulation. In 1st Workshop on X-Embodiment Robot Learning."},{"key":"e_1_3_2_2_35_1","volume-title":"Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems","author":"Qi Charles Ruizhongtai","year":"2017","unstructured":"Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. 2017. Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, Vol. 30."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00754"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"e_1_3_2_2_38_1","volume-title":"Feature splatting: Language-driven physics-based scene synthesis and editing. arXiv preprint arXiv:2404.01223","author":"Qiu Ri-Zhao","year":"2024","unstructured":"Ri-Zhao Qiu, Ge Yang, Weijia Zeng, and Xiaolong Wang. 2024. Feature splatting: Language-driven physics-based scene synthesis and editing. arXiv preprint arXiv:2404.01223 (2024)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14114696"},{"key":"e_1_3_2_2_40_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50835-1_22"},{"key":"e_1_3_2_2_42_1","volume-title":"GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding. arXiv preprint arXiv:2411.19626","author":"Shao Yawen","year":"2024","unstructured":"Yawen Shao, Wei Zhai, Yuhang Yang, Hongchen Luo, Yang Cao, and Zheng-Jun Zha. 2024. GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding. arXiv preprint arXiv:2411.19626 (2024)."},{"key":"e_1_3_2_2_43_1","volume-title":"8th Annual Conference on Robot Learning.","author":"Shorinwa Olaolu","year":"2024","unstructured":"Olaolu Shorinwa, Johnathan Tucker, Aliyah Smith, Aiden Swann, Timothy Chen, Roya Firoozi, Monroe David Kennedy, and Mac Schwager. 2024. Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splatting. In 8th Annual Conference on Robot Learning."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"MJ Swain and DH Ballard. 1991. Color indexing international journal of computer vision 7. (1991).","DOI":"10.1007\/BF00130487"},{"key":"e_1_3_2_2_45_1","volume-title":"Affordgrasp: In-context affordance reasoning for open-vocabulary task-oriented grasping in clutter. arXiv preprint arXiv:2503.00778","author":"Tang Yingbo","year":"2025","unstructured":"Yingbo Tang, Shuaike Zhang, Xiaoshuai Hao, Pengwei Wang, Jianlong Wu, Zhongyuan Wang, and Shanghang Zhang. 2025. Affordgrasp: In-context affordance reasoning for open-vocabulary task-oriented grasping in clutter. arXiv preprint arXiv:2503.00778 (2025)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"e_1_3_2_2_47_1","volume-title":"AffordDexGrasp: Open-set Language-guided Dexterous Grasp with Generalizable-Instructive Affordance. arXiv preprint arXiv:2503.07360","author":"Wei Yi-Lin","year":"2025","unstructured":"Yi-Lin Wei, Mu Lin, Yuhao Lin, Jian-Jian Jiang, Xiao-Ming Wu, Ling-An Zeng, and Wei-Shi Zheng. 2025. AffordDexGrasp: Open-set Language-guided Dexterous Grasp with Generalizable-Instructive Affordance. arXiv preprint arXiv:2503.07360 (2025)."},{"key":"e_1_3_2_2_48_1","volume-title":"Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate research","author":"Willmott Cort J","year":"2005","unstructured":"Cort J Willmott and Kenji Matsuura. 2005. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate research, Vol. 30, 1 (2005), 79-82."},{"key":"e_1_3_2_2_49_1","first-page":"60966","article-title":"Learning environment-aware affordance for 3d articulated object manipulation under occlusions","volume":"36","author":"Wu Ruihai","year":"2023","unstructured":"Ruihai Wu, Kai Cheng, Yan Zhao, Chuanruo Ning, Guanqi Zhan, and Hao Dong. 2023. Learning environment-aware affordance for 3d articulated object manipulation under occlusions. Advances in Neural Information Processing Systems, Vol. 36 (2023), 60966-60983.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01001"},{"key":"e_1_3_2_2_51_1","volume-title":"European Conference on Computer Vision. Springer, 162-179","author":"Ye Mingqiao","year":"2024","unstructured":"Mingqiao Ye, Martin Danelljan, Fisher Yu, and Lei Ke. 2024. Gaussian grouping: Segment and edit anything in 3d scenes. In European Conference on Computer Vision. Springer, 162-179."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00165"},{"key":"e_1_3_2_2_53_1","volume-title":"MoMa-Kitchen: A 100K Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation. arXiv preprint arXiv:2503.11081","author":"Zhang Pingrui","year":"2025","unstructured":"Pingrui Zhang, Xianqiang Gao, Yuhan Wu, Kehui Liu, Dong Wang, Zhigang Wang, Bin Zhao, Yan Ding, and Xuelong Li. 2025. MoMa-Kitchen: A 100K Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation. arXiv preprint arXiv:2503.11081 (2025)."},{"key":"e_1_3_2_2_54_1","volume-title":"GS-Net: Generalizable Plug-and-Play 3D Gaussian Splatting Module. arXiv preprint arXiv:2409.11307","author":"Zhang Yichen","year":"2024","unstructured":"Yichen Zhang, Zihan Wang, Jiali Han, Peilin Li, Jiaxun Zhang, Jianqiang Wang, Lei He, and Keqiang Li. 2024. GS-Net: Generalizable Plug-and-Play 3D Gaussian Splatting Module. arXiv preprint arXiv:2409.11307 (2024)."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04336-0"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"He Zhu Quyu Kong Kechun Xu Xunlong Xia Bing Deng Jieping Ye Rong Xiong and Yue Wang. 2025a. Grounding 3D Object Affordance with Language Instructions Visual Observations and Interactions. (2025).","DOI":"10.1109\/CVPR52734.2025.01616"},{"key":"e_1_3_2_2_58_1","volume-title":"Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation. arXiv preprint arXiv:2503.03556","author":"Zhu Xiaomeng","year":"2025","unstructured":"Xiaomeng Zhu, Yuyang Li, Leiyao Cui, Pengfei Li, Huan-ang Gao, Yixin Zhu, and Hao Zhao. 2025b. Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation. arXiv preprint arXiv:2503.03556 (2025)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:58:57Z","timestamp":1765342737000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754778"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3754778","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754778","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}