{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T23:04:54Z","timestamp":1789254294880,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369680","type":"print"},{"value":"9783032369697","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\/978-3-032-36969-7_2","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:17:03Z","timestamp":1789251423000},"page":"24-41","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention-DP3: Spatially Object-Aware 3D Diffusion Policy via\u00a0Geometry-Aligned Attentional Conditioning"],"prefix":"10.1007","author":[{"given":"Changbo","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongbo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zaibin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Bao, C., Xu, H., Qin, Y., Wang, X.: Dexart: benchmarking generalizable dexterous manipulation with articulated objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21190\u201321200 (2023)","DOI":"10.1109\/CVPR52729.2023.02030"},{"key":"2_CR2","unstructured":"Black, K., et\u00a0al.: $$\\pi _{0.5}$$: a vision-language-action model with open-world generalization. In: 9th Annual Conference on Robot Learning (2025)"},{"key":"2_CR3","unstructured":"Black, K., et\u00a0al.: $$\\pi _0$$: A vision-language-action flow model for general robot control. arXiv preprint arXiv:2410.24164 (2024)"},{"key":"2_CR4","unstructured":"Brohan, A., et al.: Rt-1: Robotics transformer for real-world control at scale, arXiv preprint arXiv:2212.06817 (2022)"},{"issue":"10\u201311","key":"2_CR5","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1177\/02783649241273668","volume":"44","author":"C Chi","year":"2025","unstructured":"Chi, C., et al.: Diffusion policy: visuomotor policy learning via action diffusion. Inter. J. Robot. Res. 44(10\u201311), 1684\u20131704 (2025)","journal-title":"Inter. J. Robot. Res."},{"key":"2_CR6","unstructured":"Florence, P., et al.: Implicit behavioral cloning. In: Conference on robot learning, pp. 158\u2013168. PMLR (2022)"},{"key":"2_CR7","unstructured":"Gao, D., et al.: Vita: vision-to-action flow matching policy. arXiv preprint arXiv:2507.13231 (2025)"},{"key":"2_CR8","unstructured":"Gervet, T., Xian, Z., Gkanatsios, N., Fragkiadaki, K.: Act3d: 3d feature field transformers for multi-task robotic manipulation, arXiv preprint arXiv:2306.17817 (2023)"},{"key":"2_CR9","unstructured":"Goyal, A., Xu, J., Guo, Y., Blukis, V., Chao, Y.W., Fox, D.: Rvt: robotic view transformer for 3d object manipulation. In: Conference on Robot Learning, pp. 694\u2013710. PMLR (2023)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Gu, Q., et al.: Conceptgraphs: open-vocabulary 3d scene graphs for perception and planning. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 5021\u20135028. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"2_CR11","doi-asserted-by":"publisher","first-page":"138836","DOI":"10.52202\/079017-4405","volume":"37","author":"X Hu","year":"2024","unstructured":"Hu, X., Liu, Q., Liu, X., Liu, B.: Adaflow: imitation learning with variance-adaptive flow-based policies. Adv. Neural. Inf. Process. Syst. 37, 138836\u2013138858 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: Roboground: robotic manipulation with grounded vision-language priors. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 22540\u201322550 (2025)","DOI":"10.1109\/CVPR52734.2025.02099"},{"key":"2_CR13","unstructured":"Huang, W., Wang, C., Zhang, R., Li, Y., Wu, J., Fei-Fei, L.: Voxposer: composable 3d value maps for robotic manipulation with language models, arXiv preprint arXiv:2307.05973 (2023)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Jia, Y., et\u00a0al.: Lift3d foundation policy: lifting 2d large-scale pretrained models for robust 3d robotic manipulation. arXiv preprint arXiv:2411.18623 (2024)","DOI":"10.1109\/CVPR52734.2025.01617"},{"key":"2_CR15","unstructured":"Ke, T.W., Gkanatsios, N., Fragkiadaki, K.: 3d diffuser actor: policy diffusion with 3d scene representations, arXiv preprint arXiv:2402.10885 (2024)"},{"key":"2_CR16","unstructured":"Ke, T.W., Gkanatsios, N., Xu, J., Fragkiadaki, K.: Bi3d diffuser actor: 3d policy diffusion for bi-manual robot manipulation. In: CoRL 2024 Workshop on Mastering Robot Manipulation in a World of Abundant Data (2024)"},{"key":"2_CR17","unstructured":"Kim, M.J., et al.: Openvla: an open-source vision-language-action model, arXiv preprint arXiv:2406.09246 (2024)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Li, H., Feng, Q., Zheng, Z., Feng, J., Chen, Z., Knoll, A.: Language-guided object-centric diffusion policy for generalizable and collision-aware manipulation. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 12834\u201312841. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11127231"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Liang, Z., Mu, Y., Ma, H., Tomizuka, M., Ding, M., Luo, P.: Skilldiffuser: interpretable hierarchical planning via skill abstractions in diffusion-based task execution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16467\u201316476 (2024)","DOI":"10.1109\/CVPR52733.2024.01558"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"2_CR21","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization, arXiv preprint arXiv:1711.05101 (2017)"},{"key":"2_CR22","unstructured":"Lu, G., et al.: Manicm: real-time 3d diffusion policy via consistency model for robotic manipulation, arXiv preprint arXiv:2406.01586 (2024)"},{"key":"2_CR23","unstructured":"Lu, Y., et al.: H$$^3$$DP: triply-hierarchical diffusion policy for visuomotor learning. arXiv preprint arXiv:2505.07819 (2025)"},{"key":"2_CR24","unstructured":"Mandlekar, A., et al.: What matters in learning from offline human demonstrations for robot manipulation, arXiv preprint arXiv:2108.03298 (2021)"},{"key":"2_CR25","unstructured":"Park, J., Kim, Y., Kim, S., Lee, B.J., Kim, S.: Diar: diffusion-model-guided implicit q-learning with adaptive revaluation. arXiv preprint arXiv:2410.11338 (2024)"},{"key":"2_CR26","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, pp. 815\u2013824 (2023)","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Prasad, A., Lin, K., Wu, J., Zhou, L., Bohg, J.: Consistency policy: accelerated visuomotor policies via consistency distillation, arXiv preprint arXiv:2405.07503 (2024)","DOI":"10.15607\/RSS.2024.XX.071"},{"key":"2_CR28","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"2_CR29","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"2_CR30","unstructured":"Qin, Y., Huang, B., Yin, Z.H., Su, H., Wang, X.: Dexpoint: generalizable point cloud reinforcement learning for sim-to-real dexterous manipulation. In: Conference on Robot Learning, pp. 594\u2013605. PMLR (2023)"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Rajeswaran, A., et al.: Learning complex dexterous manipulation with deep reinforcement learning and demonstrations, arXiv preprint arXiv:1709.10087 (2017)","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"2_CR32","unstructured":"Ravi, N., et\u00a0al.: Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"2_CR33","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms, arXiv preprint arXiv:1707.06347 (2017)"},{"key":"2_CR34","unstructured":"Shen, W., Yang, G., Yu, A., Wong, J., Kaelbling, L.P., Isola, P.: Distilled feature fields enable few-shot language-guided manipulation, arXiv preprint arXiv:2308.07931 (2023)"},{"key":"2_CR35","unstructured":"Shridhar, M., Manuelli, L., Fox, D.: Perceiver-actor: a multi-task transformer for robotic manipulation. In: Conference on Robot Learning, pp. 785\u2013799. PMLR (2023)"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Su, Y., et al.: Freqpolicy: efficient flow-based visuomotor policy via frequency consistency, arXiv preprint arXiv:2506.08822 (2025)","DOI":"10.52202\/085713-0937"},{"key":"2_CR37","unstructured":"Team, O.M., et al.: Octo: an open-source generalist robot policy, arXiv preprint arXiv:2405.12213 (2024)"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: Kpconv: flexible and deformable convolution for point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6411\u20136420 (2019)","DOI":"10.1109\/ICCV.2019.00651"},{"key":"2_CR39","doi-asserted-by":"publisher","first-page":"32974","DOI":"10.52202\/068431-2389","volume":"35","author":"C Wang","year":"2022","unstructured":"Wang, C., Luo, X., Ross, K., Li, D.: Vrl3: a data-driven framework for visual deep reinforcement learning. Adv. Neural. Inf. Process. Syst. 35, 32974\u201332988 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR40","unstructured":"Yang, J., Cao, Z.A., Deng, C., Antonova, R., Song, S., Bohg, J.: Equibot: Sim (3)-equivariant diffusion policy for generalizable and data efficient learning, arXiv preprint arXiv:2407.01479 (2024)"},{"key":"2_CR41","unstructured":"Yang, R., Chen, G., Wen, C., Gao, Y.: Fp3: a 3d foundation policy for robotic manipulation, arXiv preprint arXiv:2503.08950 (2025)"},{"key":"2_CR42","unstructured":"Yu, T., et al.: Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Conference on Robot Learning, pp. 1094\u20131100. PMLR (2020)"},{"issue":"12","key":"2_CR43","doi-asserted-by":"publisher","first-page":"7173","DOI":"10.1109\/TCYB.2024.3395626","volume":"54","author":"M Zare","year":"2024","unstructured":"Zare, M., Kebria, P.M., Khosravi, A., Nahavandi, S.: A survey of imitation learning: algorithms, recent developments, and challenges. IEEE Trans. Cybernet. 54(12), 7173\u20137186 (2024)","journal-title":"IEEE Trans. Cybernet."},{"key":"2_CR44","unstructured":"Ze, Y., et al.: Gnfactor: multi-task real robot learning with generalizable neural feature fields. In: Conference on Robot Learning, pp. 284\u2013301. PMLR (2023)."},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Ze, Y., Zhang, G., Zhang, K., Hu, C., Wang, M., Xu, H.: 3d diffusion policy: generalizable visuomotor policy learning via simple 3d representations. arXiv preprint arXiv:2403.03954 (2024)","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16259\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"2_CR47","unstructured":"Zhu, Y.: Vima: general robot manipulation with multimodal prompts. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"2_CR48","unstructured":"Zitkovich, B., et\u00a0al.: Rt-2: vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning, pp. 2165\u20132183. PMLR (2023)"}],"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\/978-3-032-36969-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:17:10Z","timestamp":1789251430000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36969-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369680","9783032369697"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36969-7_2","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":"13 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"}}]}}