{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:08:35Z","timestamp":1788894515586,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370341","type":"print"},{"value":"9783032370358","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37035-8_31","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:54:43Z","timestamp":1788893683000},"page":"563-580","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Geo-DPO: Aligning Semantic Intent with\u00a0Geometry for\u00a03D Affordance Segmentation"],"prefix":"10.1007","author":[{"given":"Ziqian","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianglin","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiguang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jimin","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"31_CR1","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems (2022)"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Chen, D., Kong, D., Li, J., Yin, B.: Maskprompt: open-vocabulary affordance segmentation with object shape mask prompts. In: Proceedings of the AAAI Conference on Artificial Intelligence (2025)","DOI":"10.1609\/aaai.v39i2.32200"},{"key":"31_CR3","unstructured":"Chen, Y., et al.: Grounded 3D-LLM with referent tokens. arXiv preprint arXiv:2405.10370 (2024)"},{"key":"31_CR4","unstructured":"Chu, H., et al.: 3D-affordancellm: harnessing large language models for open-vocabulary affordance detection in 3D worlds. arXiv preprint arXiv:2502.20041 (2025)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., R\u00e9, C.: Flashattention: fast and memory-efficient exact attention with IO-awareness. In: Advances in Neural Information Processing Systems (2022)","DOI":"10.52202\/068431-1189"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Deng, S., Xu, X., Wu, C., Chen, K., Jia, K.: 3D affordancenet: a benchmark for visual object affordance understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00182"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Fu, R., Liu, J., Chen, X., Nie, Y., Xiong, W.: Scene-LLM: extending language model for 3D visual understanding and reasoning. arXiv preprint arXiv:2403.11401 (2024)","DOI":"10.1109\/WACV61041.2025.00220"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"He, L., Liu, M., Ye, Q., Zhou, Y., Deng, X., Ding, G.: Task-aware 3D affordance segmentation via 2D guidance and geometric refinement. arXiv preprint arXiv:2511.11702 (2025)","DOI":"10.1609\/aaai.v40i6.42466"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Hong, Y., et al.: 3D-LLM: injecting the 3D world into large language models. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-0900"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Hou, Y., Ma, J., Sun, H., Wu, F.: Effective offline robot learning with structured task graph. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3354620"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Hou, Y., Sun, H., Ma, J., Wu, F.: Improving offline reinforcement learning with inaccurate simulators. In: 2024 IEEE International Conference on Robotics and Automation (ICRA). IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610833"},{"key":"31_CR12","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. In: ICLR, p. 3 (2022)"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Ju, Y., Hu, K., Zhang, G., Zhang, G., Jiang, M., Xu, H.: Robo-ABC: affordance generalization beyond categories via semantic correspondence for robot manipulation. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-72940-9_13"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Li, G., Sun, D., Sevilla-Lara, L., Jampani, V.: One-shot open affordance learning with foundation models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.00298"},{"key":"31_CR15","unstructured":"Li, H., Xie, H., Xu, J., Wen, B., Hong, F., Liu, Z.: MonoArt: progressive structural reasoning for monocular articulated 3D reconstruction. arXiv preprint arXiv:2603.19231 (2026)"},{"key":"31_CR16","unstructured":"Li, M., Sigal, L.: Referring transformer: a one-step approach to multi-task visual grounding. In: Advances in Neural Information Processing Systems (2021)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: 2D-DPO: scaling direct preference optimization with 2-dimensional supervision. In: Findings of the Association for Computational Linguistics: NAACL 2025 (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.455"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Ma, Z., Xiao, J., Wang, X., Yao, A.: Intermediate connectors and geometric priors for language-guided affordance segmentation on unseen object categories. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2025)","DOI":"10.1109\/ICCV51701.2025.02120"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhao, N., Xiao, J., Feng, C., Wang, X., Chua, T.S.: LASO: language-guided affordance segmentation on 3D object. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01351"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: Gres: generalized referring expression segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Visual instruction tuning. In: Levine, S. (ed.) Advances in Neural Information Processing Systems, pp. 34892\u201334916 (2023)","DOI":"10.52202\/075280-1516"},{"key":"31_CR22","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Lobo, J.M., Jim\u00e9nez-Valverde, A., Real, R.: AUC: a misleading measure of the performance of predictive distribution models. Glob. Ecol. Biogeogr. (2008)","DOI":"10.1111\/j.1466-8238.2007.00358.x"},{"key":"31_CR24","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Luo, J., et al.: 3D-SPS: single-stage 3D visual grounding via referred point progressive selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Mo, K., et al.: Partnet: a large-scale benchmark for fine-grained and hierarchical part-level 3D object understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00100"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Nasiriany, S., et al.: RT-affordance: affordances are versatile intermediate representations for robot manipulation. In: 2025 IEEE International Conference on Robotics and Automation (ICRA). IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11127525"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Nguyen, T.T., Wilson, C., Dalins, J.: Aligning large vision-language models by deep reinforcement learning and direct preference optimization. arXiv preprint arXiv:2509.06759 (2025)","DOI":"10.1109\/ACAI68217.2025.11406573"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Ning, C., Wu, R., Lu, H., Mo, K., Dong, H.: Where2explore: few-shot affordance learning for unseen novel categories of articulated objects. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-0203"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Peng, S., Genova, K., Jiang, C., Tagliasacchi, A., Pollefeys, M., Funkhouser, T.: Openscene: 3D scene understanding with open vocabularies. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"31_CR31","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems (2017)"},{"key":"31_CR32","unstructured":"Qi, Z., et al.: Shapellm: universal 3D object understanding for embodied interaction. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024 (2025)"},{"key":"31_CR33","doi-asserted-by":"crossref","unstructured":"Qian, S., Chen, W., Bai, M., Zhou, X., Tu, Z., Li, L.E.: Affordancellm: grounding affordance from vision language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPRW63382.2024.00754"},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-2338"},{"key":"31_CR35","doi-asserted-by":"crossref","unstructured":"Rahman, M.A., Wang, Y.: Optimizing intersection-over-union in deep neural networks for image segmentation. In: International Symposium on Visual Computing (2016)","DOI":"10.1007\/978-3-319-50835-1_22"},{"key":"31_CR36","doi-asserted-by":"crossref","unstructured":"Roy, A., Todorovic, S.: A multi-scale CNN for affordance segmentation in RGB images. In: European Conference on Computer Vision (2016)","DOI":"10.1007\/978-3-319-46493-0_12"},{"key":"31_CR37","doi-asserted-by":"crossref","unstructured":"Shao, Y., Zhai, W., Yang, Y., Luo, H., Cao, Y., Zha, Z.J.: Great: geometry-intention collaborative inference for open-vocabulary 3D object affordance grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.01615"},{"key":"31_CR38","doi-asserted-by":"crossref","unstructured":"Swain, M.J., Ballard, D.H.: Color indexing. Int. J. Comput. Vision (1991)","DOI":"10.1007\/BF00130487"},{"key":"31_CR39","doi-asserted-by":"crossref","unstructured":"Wallace, B., et al.: Diffusion model alignment using direct preference optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Visionllm: large language model is also an open-ended decoder for vision-centric tasks. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-2688"},{"key":"31_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. (TOG) (2019)","DOI":"10.1145\/3326362"},{"key":"31_CR42","unstructured":"Wang, Z., Huang, H., Zhao, Y., Zhang, Z., Zhao, Z.: Chat-3d: data-efficiently tuning large language model for universal dialogue of 3D scenes. arXiv preprint arXiv:2308.08769 (2023)"},{"key":"31_CR43","doi-asserted-by":"crossref","unstructured":"Willmott, C.J., Matsuura, K.: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Res. (2005)","DOI":"10.3354\/cr030079"},{"key":"31_CR44","doi-asserted-by":"crossref","unstructured":"Wu, D., et al.: Ragnet: large-scale reasoning-based affordance segmentation benchmark towards general grasping. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.01114"},{"key":"31_CR45","doi-asserted-by":"crossref","unstructured":"Wu, R., Cheng, K., Zhao, Y., Ning, C., Zhan, G., Dong, H.: Learning environment-aware affordance for 3D articulated object manipulation under occlusions. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-2664"},{"key":"31_CR46","doi-asserted-by":"crossref","unstructured":"Wu, S., et al.: Afforddp: generalizable diffusion policy with transferable affordance. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.00654"},{"key":"31_CR47","doi-asserted-by":"crossref","unstructured":"Xie, Y., Li, G., Xu, X., Kan, M.Y.: V-DPO: mitigating hallucination in large vision language models via vision-guided direct preference optimization. In: Findings of the Association for Computational Linguistics: EMNLP 2024 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.775"},{"key":"31_CR48","doi-asserted-by":"crossref","unstructured":"Xing, S., et al.: Re-align: aligning vision language models via retrieval-augmented direct preference optimization. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.121"},{"key":"31_CR49","unstructured":"Xu, C., Chen, Y., Wang, H., Zhu, S.C., Zhu, Y., Huang, S.: Partafford: part-level affordance discovery from 3D objects. arXiv preprint arXiv:2202.13519 (2022)"},{"key":"31_CR50","unstructured":"Xu, P., Mu, Y.: Weakly-supervised affordance grounding guided by part-level semantic priors. arXiv preprint arXiv:2505.24103 (2025)"},{"key":"31_CR51","doi-asserted-by":"crossref","unstructured":"Xu, R., Wang, X., Wang, T., Chen, Y., Pang, J., Lin, D.: Pointllm: empowering large language models to understand point clouds. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"31_CR52","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhai, W., Luo, H., Cao, Y., Luo, J., Zha, Z.J.: Grounding 3D object affordance from 2D interactions in images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01001"},{"key":"31_CR53","unstructured":"Yang, Z., Qiu, X., Zhao, X., Wang, X., Zhang, Q., Xiao, J.: Frequency-aware affinity for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20468\u201320477 (2026)"},{"key":"31_CR54","unstructured":"Yang, Z., Zhao, X., Wang, X., Zhang, Q., Xiao, J.: Leveraging class distributions in clip for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 34714\u201334723 (2026)"},{"key":"31_CR55","unstructured":"You, H., et al.: Ferret: refer and ground anything anywhere at any granularity. arXiv preprint arXiv:2310.07704 (2023)"},{"key":"31_CR56","doi-asserted-by":"crossref","unstructured":"Yu, C., et al.: Seqafford: sequential 3D affordance reasoning via multimodal large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.00165"},{"key":"31_CR57","unstructured":"Zhou, J., Wang, J., Ma, B., Liu, Y.S., Huang, T., Wang, X.: Uni3d: exploring unified 3D representation at scale. In: International Conference on Learning Representations (2024)"},{"key":"31_CR58","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"key":"31_CR59","doi-asserted-by":"crossref","unstructured":"Zhu, L., et al.: Popen: preference-based optimization and ensemble for LVLM-based reasoning segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.02814"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37035-8_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:54:51Z","timestamp":1788893691000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37035-8_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370341","9783032370358"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37035-8_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}