{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:13:27Z","timestamp":1789074807280,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032368454","type":"print"},{"value":"9783032368461","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\/978-3-032-36846-1_24","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:02:01Z","timestamp":1789074121000},"page":"386-404","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Token-Based Affordance Grounding with\u00a0Large Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2069-2528","authenticated-orcid":false,"given":"Seung Il","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6429-2722","authenticated-orcid":false,"given":"Qinqian","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4621-881X","authenticated-orcid":false,"given":"Daguang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5031-4337","authenticated-orcid":false,"given":"Dong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7532-6919","authenticated-orcid":false,"given":"Robby T.","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5275-3665","authenticated-orcid":false,"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0127-2281","authenticated-orcid":false,"given":"Bo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"24_CR1","unstructured":"Ard\u00f3n, P., Pairet, \u00c8., Lohan, K.S., Ramamoorthy, S., Petrick, R.: Affordances in robotic tasks\u2013a survey. arXiv preprint arXiv:2004.07400 (2020)"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Bahl, S., Mendonca, R., Chen, L., Jain, U., Pathak, D.: Affordances from human videos as a versatile representation for robotics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13778\u201313790 (2023)","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"24_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL Technical report, arXiv preprint arXiv:2511.21631 (2025)"},{"key":"24_CR4","unstructured":"Brohan, A., et al.: Do as i can, not as i say: grounding language in robotic affordances. In: Conference on Robot Learning, pp. 287\u2013318. PMLR (2023)"},{"key":"24_CR5","unstructured":"Cao, X., et\u00a0al.: Smart-Insertion-V: photorealistic video insertion via a closed-loop feedback dual-stream framework. arXiv preprint arXiv:2605.23891 (2026)"},{"key":"24_CR6","unstructured":"Carion, N., et al.: SAM 3: segment anything with concepts (2025)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 381\u2013389. IEEE (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 782\u2013791 (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Chuang, C.Y., Li, J., Torralba, A., Fidler, S.: Learning to act properly: Predicting and explaining affordances from images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 975\u2013983 (2018)","DOI":"10.1109\/CVPR.2018.00108"},{"issue":"11","key":"24_CR10","doi-asserted-by":"publisher","first-page":"4125","DOI":"10.1109\/TPAMI.2020.2991965","volume":"43","author":"D Damen","year":"2020","unstructured":"Damen, D., et al.: The epic-kitchens dataset: collection, challenges and baselines. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 4125\u20134141 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Gao, W., et al.: TS-CAM: token semantic coupled attention map for weakly supervised object localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2886\u20132895 (2021)","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"24_CR12","unstructured":"Ghiasi, A., et al.: What do vision transformers learn? a visual exploration. arXiv preprint arXiv:2212.06727 (2022)"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Gibson, J.J.: The ecological approach to visual perception: classic edition, Psychology press (2014)","DOI":"10.4324\/9781315740218"},{"issue":"3","key":"24_CR14","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":"24_CR15","doi-asserted-by":"crossref","unstructured":"Jang, J.H., Seo, H., Chun, S.Y.: Intra: Interaction relationship-aware weakly supervised affordance grounding. In: European Conference on Computer Vision, pp. 18\u201334. Springer (2024)","DOI":"10.1007\/978-3-031-73039-9_2"},{"key":"24_CR16","unstructured":"Kang, S., Kim, J., Kim, J., Hwang, S.J.: See what you are told: Visual attention sink in large multimodal models. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Kang, S., Kim, J., Kim, J., Hwang, S.J.: Your large vision-language model only needs a few attention heads for visual grounding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 9339\u20139350 (2025)","DOI":"10.1109\/CVPR52734.2025.00872"},{"key":"24_CR18","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 4015\u20134026 (2023)"},{"issue":"8","key":"24_CR19","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1177\/0278364913478446","volume":"32","author":"HS Koppula","year":"2013","unstructured":"Koppula, H.S., Gupta, R., Saxena, A.: Learning human activities and object affordances from RGB-D videos. Int. J. Robot. Res. 32(8), 951\u2013970 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Lei, Q., Wang, B., Robby, T., T.: Hola: Zero-shot hoi detection with low-rank decomposed vlm feature adaptation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.00178"},{"key":"24_CR21","doi-asserted-by":"publisher","first-page":"55831","DOI":"10.52202\/079017-1775","volume":"37","author":"Q Lei","year":"2024","unstructured":"Lei, Q., Wang, B., Tan, R.: EZ-HOI: VLM adaptation via guided prompt learning for zero-shot hoi detection. Adv. Neural. Inf. Process. Syst. 37, 55831\u201355857 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR22","unstructured":"Lei, Q., Wang, B., Tan, R.T.: CrossHOI-Bench: a unified benchmark for hoi evaluation across vision-language models and hoi-specific methods. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2026)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Li, G., Jampani, V., Sun, D., Sevilla-Lara, L.: Locate: Localize and transfer object parts for weakly supervised affordance grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10922\u201310931 (2023)","DOI":"10.1109\/CVPR52729.2023.01051"},{"key":"24_CR24","unstructured":"Liu, J., et\u00a0al.: Tele-Omni: a unified multimodal framework for video generation and editing. arXiv preprint arXiv:2602.09609 (2026)"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: European Conference on Computer Vision, pp. 38\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"24_CR26","unstructured":"Lu, P., et al.: MathVista: evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7086\u20137096 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y., Tao, D.: Learning affordance grounding from exocentric images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2252\u20132261 (2022)","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Ma, K., Dong, H., Mu, Y.: Local occupancy-enhanced object grasping with multiple triplanar projection. In: European Conference on Computer Vision, pp. 1\u201318. Springer (2024)","DOI":"10.1007\/978-3-031-72904-1_1"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Mai, J., Yang, M., Luo, W.: Erasing integrated learning: a simple yet effective approach for weakly supervised object localization. In: CVPR, pp. 8766\u20138775 (2020)","DOI":"10.1109\/CVPR42600.2020.00879"},{"key":"24_CR31","unstructured":"Michel, P., Levy, O., Neubig, G.: Are sixteen heads really better than one? Adv. Neural Inf. Proces. Syst. 32 (2019)"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Moon, W., Seong, H.S., Heo, J.P.: Selective contrastive learning for weakly supervised affordance grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5210\u20135220 (2025)","DOI":"10.1109\/ICCV51701.2025.00495"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Mur-Labadia, L., Guerrero, J.J., Martinez-Cantin, R.: Multi-label affordance mapping from egocentric vision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5238\u20135249 (2023)","DOI":"10.1109\/ICCV51070.2023.00483"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Myers, A., Kanazawa, A., Fermuller, C., Aloimonos, Y.: Affordance of object parts from geometric features. In: International Conference on Robotics and Automation 2, pp. 5\u20136 (2015)","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Pan, X., et al.: Unveiling the potential of structure preserving for weakly supervised object localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11642\u201311651 (2021)","DOI":"10.1109\/CVPR46437.2021.01147"},{"key":"24_CR36","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 PMLR (2021)"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Sawatzky, J., Srikantha, A., Gall, J.: Weakly supervised affordance detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2795\u20132804 (2017)","DOI":"10.1109\/CVPR.2017.552"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Going denser with open-vocabulary part segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15453\u201315465 (2023)","DOI":"10.1109\/ICCV51070.2023.01417"},{"key":"24_CR39","doi-asserted-by":"crossref","unstructured":"Tang, J., Wei, Z., Zheng, G., Yang, S.: Closed-loop transfer for weakly-supervised affordance grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9530\u20139539 (2025)","DOI":"10.1109\/ICCV51701.2025.00889"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Wu, J., Kang, W., Tang, H., Hong, Y., Yan, Y.: On the faithfulness of vision transformer explanations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10936\u201310945 (2024)","DOI":"10.1109\/CVPR52733.2024.01040"},{"key":"24_CR41","unstructured":"Wu, Z., et\u00a0al.: DeepSeek-VL2: mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Xu, L., Gao, Y., Song, W., Hao, A.: Weakly supervised multimodal affordance grounding for egocentric images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 6324\u20136332. (2024)","DOI":"10.1609\/aaai.v38i6.28451"},{"key":"24_CR43","unstructured":"Xu, P., Mu, Y.: Weakly-supervised affordance grounding guided by part-level semantic priors. arXiv preprint arXiv:2505.24103 (2025)"},{"key":"24_CR44","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, pp. 10905\u201310915 (2023)","DOI":"10.1109\/ICCV51070.2023.01001"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9556\u20139567 (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"24_CR46","unstructured":"Zhang, J., Khayatkhoei, M., Chhikara, P., Ilievski, F.: MLLMs know where to look: training-free perception of small visual details with multimodal LLMs. arXiv preprint arXiv:2502.17422 (2025)"},{"key":"24_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"24_CR48","unstructured":"Zhu, J., et al.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"}],"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\/978-3-032-36846-1_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:02:09Z","timestamp":1789074129000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36846-1_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032368454","9783032368461"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36846-1_24","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":"11 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"}}]}}