{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:06:51Z","timestamp":1789124811630,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372604","type":"print"},{"value":"9783032372611","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\/978-3-032-37261-1_26","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:17:17Z","timestamp":1789121837000},"page":"450-468","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HOIMask: Towards Generative Masked Modeling for\u00a0Human Object Interaction Generation"],"prefix":"10.1007","author":[{"given":"Yihong","family":"Ji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinsong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B.L., Xie, X., Petrov, I.A., Sminchisescu, C., Theobalt, C., Pons-Moll, G.: Behave: dataset and method for tracking human object interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15935\u201315946 (2022)","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Cha, J., Kim, J., Yoon, J.S., Baek, S.: Text2hoi: text-guided 3D motion generation for hand-object interaction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1577\u20131585 (2024)","DOI":"10.1109\/CVPR52733.2024.00156"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: Maskgit: masked generative image transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Executing your commands via motion diffusion in latent space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18000\u201318010 (2023)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Christen, S., et al.: Diffh2o: diffusion-based synthesis of hand-object interactions from textual descriptions. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3680528.3687563"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Cong, P., Wang, Z., Ma, Y., Yue, X.: Semgeomo: dynamic contextual human motion generation with semantic and geometric guidance. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17561\u201317570 (2025)","DOI":"10.1109\/CVPR52734.2025.01636"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mughal, M.H., Golyanik, V., Theobalt, C.: Mofusion: a framework for denoising-diffusion-based motion synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9760\u20139770 (2023)","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Dai, W., Chen, L.H., Wang, J., Liu, J., Dai, B., Tang, Y.: Motionlcm: real-time controllable motion generation via latent consistency model. In: European Conference on Computer Vision, pp. 390\u2013408 (2024)","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"26_CR9","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Diller, C., Dai, A.: Cg-hoi: contact-guided 3D human-object interaction generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19888\u201319901 (2024)","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Guo, C., Mu, Y., Javed, M.G., Wang, S., Cheng, L.: Momask: generative masked modeling of 3d human motions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1900\u20131910 (2024)","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Generating diverse and natural 3D human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5152\u20135161 (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Guo, C., Zuo, X., Wang, S., Cheng, L.: Tm2t: stochastic and tokenized modeling for the reciprocal generation of 3d human motions and texts. In: European Conference on Computer Vision, pp. 580\u2013597 (2022)","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"He, W., Liu, Y., Liu, R., Yi, L.: Syncdiff: synchronized motion diffusion for multi-body human-object interaction synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11731\u201311743 (2025)","DOI":"10.1109\/ICCV51701.2025.01091"},{"key":"26_CR15","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR16","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021)"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Huang, G., Zeng, L.A., Zheng, Z., Gu, S., Zheng, W.S.: Efficient explicit joint-level interaction modeling with mamba for text-guided hoi generation. arXiv preprint arXiv:2503.23121 (2025)","DOI":"10.1109\/ICME59968.2025.11209856"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Huang, M., et al.: Hoigpt: learning long-sequence hand-object interaction with language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7136\u20137146 (2025)","DOI":"10.1109\/CVPR52734.2025.00669"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Y., Taheri, O., Black, M.J., Tzionas, D.: Intercap: joint markerless 3D tracking of humans and objects in interaction. In: DAGM German Conference on Pattern Recognition, pp. 281\u2013299. Springer (2022)","DOI":"10.1007\/978-3-031-16788-1_18"},{"key":"26_CR20","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with Gumbel-softmax. In: The fifth International Conference on Learning Representations (2017)"},{"key":"26_CR21","unstructured":"Javed, M.G., Li, X., et al.: Intermask: 3D human interaction generation via collaborative masked modeling. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"26_CR22","unstructured":"Jeong, M., Hwang, Y., Lee, J., Jung, S., Kim, W.H.: Hgm3: hierarchical generative masked motion modeling with hard token mining. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Ji, Y., et al.: Onlinehoi: towards online human-object interaction generation and perception. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 9395\u20139403 (2025)","DOI":"10.1145\/3746027.3754848"},{"key":"26_CR24","doi-asserted-by":"publisher","first-page":"20067","DOI":"10.52202\/075280-0880","volume":"36","author":"B Jiang","year":"2023","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: Motiongpt: human motion as a foreign language. Adv. Neural. Inf. Process. Syst. 36, 20067\u201320079 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Jiang, H., Liu, S., Wang, J., Wang, X.: Hand-object contact consistency reasoning for human grasps generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11107\u201311116 (2021)","DOI":"10.1109\/ICCV48922.2021.01092"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Jin, P., et al.: Local action-guided motion diffusion model for text-to-motion generation. In: European Conference on Computer Vision, pp. 392\u2013409 (2024)","DOI":"10.1007\/978-3-031-72698-9_23"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Li, J., Clegg, A., Mottaghi, R., Wu, J., Puig, X., Liu, C.K.: Controllable human-object interaction synthesis. In: European Conference on Computer Vision, pp. 54\u201372 (2024)","DOI":"10.1007\/978-3-031-72940-9_4"},{"issue":"6","key":"26_CR28","first-page":"1","volume":"42","author":"J Li","year":"2023","unstructured":"Li, J., Wu, J., Liu, C.K.: Object motion guided human motion synthesis. ACM Trans. Graphics (TOG) 42(6), 1\u201311 (2023)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, Y.L., Zeng, A., Zhou, Z., You, Y., Lu, C.: Bridging the gap between human motion and action semantics via kinematic phrases. In: European Conference on Computer Vision, pp. 223\u2013240 (2024)","DOI":"10.1007\/978-3-031-73242-3_13"},{"issue":"6","key":"26_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: a skinned multi-person linear model. ACM Trans. Graphics (TOG) 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Lu, J., Huang, C.H.P., Bhattacharya, U., Huang, Q., Zhou, Y.: Humoto: a 4D dataset of mocap human object interactions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10886\u201310897 (2025)","DOI":"10.1109\/ICCV51701.2025.01013"},{"key":"26_CR32","unstructured":"Lu, S., et al.: Humantomato: text-aligned whole-body motion generation. In: Proceedings of the 41st International Conference on Machine Learning, pp. 32939\u201332977 (2024)"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Lucas, T., Baradel, F., Weinzaepfel, P., Rogez, G.: Posegpt: Quantization-based 3D human motion generation and forecasting. In: European Conference on Computer Vision, pp. 417\u2013435 (2022)","DOI":"10.1007\/978-3-031-20068-7_24"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Meng, Z., Xie, Y., Peng, X., Han, Z., Jiang, H.: Rethinking diffusion for text-driven human motion generation: Redundant representations, evaluation, and masked autoregression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27859\u201327871 (2025)","DOI":"10.1109\/CVPR52734.2025.02594"},{"key":"26_CR35","unstructured":"Parmar, N., et al.: Image transformer. In: International Conference on Machine Learning, pp. 4055\u20134064. PMLR (2018)"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Peng, X., Xie, Y., Wu, Z., Jampani, V., Sun, D., Jiang, H.: Hoi-diff: text-driven synthesis of 3d human-object interactions using diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 2878\u20132888 (2025)","DOI":"10.1109\/CVPRW67362.2025.00271"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Petrov, I.A., Marin, R., Chibane, J., Pons-Moll, G.: Tridi: trilateral diffusion of 3D humans, objects, and interactions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5523\u20135535 (2025)","DOI":"10.1109\/ICCV51701.2025.00524"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Pinyoanuntapong, E., et al.: Maskcontrol: spatio-temporal control for masked motion synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9955\u20139965 (2025)","DOI":"10.1109\/ICCV51701.2025.00928"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Pinyoanuntapong, E., Saleem, M.U., Wang, P., Lee, M., Das, S., Chen, C.: Bamm: bidirectional autoregressive motion model. In: European Conference on Computer Vision, pp. 172\u2013190 (2024)","DOI":"10.1007\/978-3-031-72633-0_10"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Pinyoanuntapong, E., Wang, P., Lee, M., Chen, C.: Mmm: generative masked motion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1546\u20131555 (2024)","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"26_CR42","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38st International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Ren, Z., Huang, S., Li, X.: Realistic human motion generation with cross-diffusion models. In: European Conference on Computer Vision, pp. 345\u2013362 (2024)","DOI":"10.1007\/978-3-031-72661-3_20"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"26_CR45","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: The Ninth International Conference on Learning Representations (2021)"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Song, W., et al.: Hoianimator: generating text-prompt human-object animations using novel perceptive diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 811\u2013820 (2024)","DOI":"10.1109\/CVPR52733.2024.00083"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Taheri, O., Ghorbani, N., Black, M.J., Tzionas, D.: Grab: a dataset of wholebody human grasping of objects. In: European Conference on Computer Vision, pp. 581\u2013600. Springer (2020)","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"26_CR48","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-or, D., Bermano, A.H.: Human motion diffusion model. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"26_CR49","doi-asserted-by":"publisher","first-page":"84839","DOI":"10.52202\/079017-2694","volume":"37","author":"K Tian","year":"2024","unstructured":"Tian, K., Jiang, Y., Yuan, Z., Peng, B., Wang, L.: Visual autoregressive modeling: scalable image generation via next-scale prediction. Adv. Neural. Inf. Process. Syst. 37, 84839\u201384865 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR50","unstructured":"Van Den Oord, A., Vinyals, O., et al.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"26_CR51","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"26_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Y., Leng, Z., Li, F.W., Wu, S.C., Liang, X.: FG-t2m: fine-grained text-driven human motion generation via diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22035\u201322044 (2023)","DOI":"10.1109\/ICCV51070.2023.02014"},{"issue":"1","key":"26_CR53","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s10032-020-00360-2","volume":"24","author":"Z Wang","year":"2021","unstructured":"Wang, Z., Liu, J.C.: Translating math formula images to latex sequences using deep neural networks with sequence-level training. Int. J. Document Anal. Recogn. (IJDAR) 24(1), 63\u201375 (2021)","journal-title":"Int. J. Document Anal. Recogn. (IJDAR)"},{"key":"26_CR54","unstructured":"Wang, Z., et al.: Unleashing guidance without classifiers for human-object interaction animation. In: The Fourteenth International Conference on Learning Representations (2026)"},{"key":"26_CR55","doi-asserted-by":"crossref","unstructured":"Wu, L., Chen, Z., Lan, J.: Hoi-dyn: learning interaction dynamics for human object motion diffusion. arXiv preprint arXiv:2507.01737 (2025)","DOI":"10.52202\/085713-3037"},{"key":"26_CR56","doi-asserted-by":"crossref","unstructured":"Wu, Z., Li, J., Xu, P., Liu, C.K.: Human-object interaction from human-level instructions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11176\u201311186 (2025)","DOI":"10.1109\/ICCV51701.2025.01040"},{"key":"26_CR57","doi-asserted-by":"crossref","unstructured":"Xu, S., Li, Z., Wang, Y.X., Gui, L.Y.: Interdiff: generating 3D human-object interactions with physics-informed diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14928\u201314940 (2023)","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"26_CR58","doi-asserted-by":"crossref","unstructured":"Xue, M., Liu, Y., Guo, L., Huang, S., Ding, C.: Guiding human-object interactions with rich geometry and relations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22714\u201322723 (2025)","DOI":"10.1109\/CVPR52734.2025.02115"},{"key":"26_CR59","doi-asserted-by":"crossref","unstructured":"Yuksel, C.: Sample elimination for generating Poisson disk sample sets. In: Computer Graphics Forum, vol. 34, pp. 25\u201332. Wiley Online Library (2015)","DOI":"10.1111\/cgf.12538"},{"key":"26_CR60","doi-asserted-by":"crossref","unstructured":"Zeng, L.A., et al.: Chainhoi: joint-based kinematic chain modeling for human-object interaction generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12358\u201312369 (2025)","DOI":"10.1109\/CVPR52734.2025.01153"},{"key":"26_CR61","doi-asserted-by":"crossref","unstructured":"Zeng, L.A., Huang, G., Wu, G., Zheng, W.S.: Light-t2m: a lightweight and fast model for text-to-motion generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 9797\u20139805 (2025)","DOI":"10.1609\/aaai.v39i9.33062"},{"key":"26_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Generating human motion from textual descriptions with discrete representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14730\u201314740 (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"issue":"6","key":"26_CR63","doi-asserted-by":"publisher","first-page":"4115","DOI":"10.1109\/TPAMI.2024.3355414","volume":"46","author":"M Zhang","year":"2024","unstructured":"Zhang, M., et al.: Motiondiffuse: text-driven human motion generation with diffusion model. IEEE Trans. Pattern Anal. Mach. Intell. 46(6), 4115\u20134128 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, M., et al.: Remodiffuse: retrieval-augmented motion diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 364\u2013373 (2023)","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"26_CR65","doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: I\u2019m hoi: inertia-aware monocular capture of 3D human-object interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 729\u2013741 (2024)","DOI":"10.1109\/CVPR52733.2024.00076"},{"key":"26_CR66","doi-asserted-by":"crossref","unstructured":"Zhong, C., Hu, L., Zhang, Z., Xia, S.: Attt2m: text-driven human motion generation with multi-perspective attention mechanism. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 509\u2013519 (2023)","DOI":"10.1109\/ICCV51070.2023.00053"},{"key":"26_CR67","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Wan, Y., Wang, B.: Avatargpt: all-in-one framework for motion understanding planning generation and beyond. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1357\u20131366 (2024)","DOI":"10.1109\/CVPR52733.2024.00135"},{"key":"26_CR68","doi-asserted-by":"crossref","unstructured":"Zou, Q., et al.: Parco: part-coordinating text-to-motion synthesis. In: European Conference on Computer Vision, pp. 126\u2013143 (2024)","DOI":"10.1007\/978-3-031-72992-8_8"}],"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\/978-3-032-37261-1_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:17:39Z","timestamp":1789121859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37261-1_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372604","9783032372611"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37261-1_26","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":"12 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"}}]}}