{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:02:35Z","timestamp":1790276555785,"version":"4.1.0"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369833","type":"print"},{"value":"9783032369840","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\/978-3-032-36984-0_11","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:57:21Z","timestamp":1790276241000},"page":"195-211","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TAIHRI: Task-Aware 3D Human Keypoints Localization for\u00a0Close-Range Human-Robot Interaction"],"prefix":"10.1007","author":[{"given":"Ao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonggen","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuji","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS, vol. 35, pp. 23716\u201323736 (2022)","DOI":"10.52202\/068431-1723"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Baradel, F., et al.: Multi-HMR: multi-person whole-body human mesh recovery in a single shot. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73337-6_12"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Black, M.J., Patel, P., Tesch, J., Yang, J.: BEDLAM: a synthetic dataset of bodies exhibiting detailed lifelike animated motion. In: CVPR, pp. 8726\u20138737 (2023)","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"11_CR4","unstructured":"Cai, Z., et al.: DepthLM: metric depth from vision language models. arXiv preprint: arXiv:2509.25413 (2025)"},{"key":"11_CR5","unstructured":"Chen, T., Saxena, S., Li, L., Fleet, D.J., Hinton, G.: Pix2Seq: a language modeling framework for object detection. arXiv preprint: arXiv:2109.10852 (2021)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Park, J., Lee, K.M.: Learning to estimate robust 3D human mesh from in-the-wild crowded scenes. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00153"},{"key":"11_CR7","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint: arXiv:2507.06261 (2025)"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Feng, D., Guo, P., Peng, E., Zhu, M., Yu, W., Wang, P.: PoseLLaVA: pose centric multimodal LLM for fine-grained 3D pose manipulation. In: AAAI, vol. 39, pp. 2951\u20132959 (2025)","DOI":"10.1609\/aaai.v39i3.32302"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Feng, Y., Lin, J., Dwivedi, S.K., Sun, Y., Patel, P., Black, M.J.: ChatPose: chatting about 3D human pose. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00204"},{"key":"11_CR10","unstructured":"Ge, Y., Wang, W., Chen, Y., Chen, H., Shen, C.: 3D human reconstruction in the wild with synthetic data using generative models. arXiv preprint: arXiv:2403.11111 (2024)"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Goel, S., Pavlakos, G., Rajasegaran, J., Kanazawa, A., Malik, J.: Reconstructing and tracking humans with transformers. ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"11_CR12","unstructured":"Huo, Y., Li, A., Dai, W., Wu, S., Tang, Y.: BridgeDiffusion: latent space optimization for independent body-part generation with motion consistency bridges in interactive dance. In: CVPR Findings, pp. 3449\u20133459 (2026)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE TPAMI 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"11_CR14","unstructured":"Jiang, Q., et al.: Detect anything via next point prediction. arXiv preprint: arXiv:2510.12798 (2025)"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: CVPR, pp. 7122\u20137131(2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Song, J.T., Cao, J., Luo, Z., Kitani, K.: Harmony4D: a video dataset for in-the-wild close human interactions. In: NeurIPS, vol. 37, pp. 107270\u2013107285 (2024)","DOI":"10.52202\/079017-3407"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Tripathi, S., Kitani, K.: Occluded human mesh recovery. In: CVPR, pp. 1715\u20131725 (2022)","DOI":"10.1109\/CVPR52688.2022.00176"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: PARE: part attention regressor for 3D human body estimation. In: ICCV, pp. 11127\u201311137 (2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Li, A., Liu, J., Zhu, Y., Tang, Y.: ScoreHOI: physically plausible reconstruction of human-object interaction via score-guided diffusion. In: ICCV, pp. 7592\u20137602 (2025)","DOI":"10.1109\/ICCV51701.2025.00712"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Li, J., Yang, Z., Wang, X., Ma, J., Zhou, C., Yang, Y.: JOTR: 3D joint contrastive learning with transformers for occluded human mesh recovery. In: ICCV, pp. 9110\u20139121 (2023)","DOI":"10.1109\/ICCV51070.2023.00836"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Li, R., Li, S., Kong, L., Yang, X., Liang, J.: SeeGround: see and ground for zero-shot open-vocabulary 3D visual grounding. In: CVPR, pp. 3707\u20133717 (2025)","DOI":"10.1109\/CVPR52734.2025.00351"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, J., Zhang, Z., Xu, S., Yan, Y.: CLIFF: carrying location information in full frames into human pose and shape estimation. In: ECCV, pp. 590\u2013606. Springer (2022)","DOI":"10.1007\/978-3-031-20065-6_34"},{"key":"11_CR23","unstructured":"Lin, H., et al.: Depth anything 3: recovering the visual space from any views. arXiv preprint: arXiv:2511.10647 (2025)"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Lin, J., Feng, Y., Liu, W., Black, M.J.: ChatHuman: chatting about 3D humans with tools. In: CVPR, pp. 8150\u20138161 (2025)","DOI":"10.1109\/CVPR52734.2025.00763"},{"issue":"6","key":"11_CR25","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 TOG 34(6), 1\u201316 (2015)","journal-title":"ACM TOG"},{"key":"11_CR26","unstructured":"Man, Y., et al.: LocateAnything3D: vision-language 3D detection with chain-of-sight. In: CVPR, pp. 31089\u201331102 (2026)"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 3DV. IEEE (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Meyer, G.P.: An alternative probabilistic interpretation of the Huber loss. In: CVPR, pp. 5261\u20135269 (2021)","DOI":"10.1109\/CVPR46437.2021.00522"},{"key":"11_CR29","unstructured":"OpenAI: GPT-4V system card (2025). https:\/\/openai.com\/index\/gpt-4v-system-card\/. Accessed 24 Jan 2026"},{"key":"11_CR30","unstructured":"OpenAI: Introducing GPT-5 (2025). https:\/\/openai.com\/index\/introducing-gpt-5\/. Accessed 24 Jan 2026"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Patel, P., Black, M.J.: CameraHMR: aligning people with perspective. 3DV (2025)","DOI":"10.1109\/3DV66043.2025.00146"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Patel, P., Huang, C.H.P., Tesch, J., Hoffmann, D.T., Tripathi, S., Black, M.J.: AGORA: avatars in geography optimized for regression analysis. In: CVPR, pp. 13468\u201313478 (2021)","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Rempe, D., Birdal, T., Hertzmann, A., Yang, J., Sridhar, S., Guibas, L.J.: HUMOR: 3D human motion model for robust pose estimation. In: ICCV, pp. 11488\u201311499 (2021)","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"11_CR35","unstructured":"Shao, Z., et\u00a0al.: DeepseekMath: pushing the limits of mathematical reasoning in open language models. arXiv preprint: arXiv:2402.03300 (2024)"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Su, C., Ma, X., Su, J., Wang, Y.: SAT-HMR: real-time multi-person 3D mesh estimation via scale-adaptive tokens. In: CVPR, pp. 16796\u201316806 (2025)","DOI":"10.1109\/CVPR52734.2025.01565"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Tesch, J., et al.: BEDLAM2.0: synthetic humans and cameras in motion (2025)","DOI":"10.52202\/085713-1628"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Zolly: zoom focal length correctly for perspective-distorted human mesh reconstruction. In: ICCV, pp. 3925\u20133935 (2023)","DOI":"10.1109\/ICCV51070.2023.00363"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Y., Patel, P., Daniilidis, K., Black, M.J., Kocabas, M.: PromptHMR: promptable human mesh recovery. In: CVPR, pp. 1148\u20131159 (2025)","DOI":"10.1109\/CVPR52734.2025.00115"},{"key":"11_CR40","unstructured":"Wang, Y., Liu, W., Niu, J., Zhang, H., Tang, Y.: VG-Refiner: towards tool-refined referring grounded reasoning via agentic reinforcement learning. arXiv preprint: arXiv:2512.06373 (2025)"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, H., Liu, Y., Li, J., Tang, Y.: SAM2-LOVE: segment anything model 2 in language-aided audio-visual scenes. In: CVPR, pp. 28932\u201328941 (2025)","DOI":"10.1109\/CVPR52734.2025.02694"},{"key":"11_CR42","unstructured":"Wang, Y., et al.: N3D-VLM: native 3D grounding enables accurate spatial reasoning in vision-language models. arXiv preprint: arXiv:2512.16561 (2025)"},{"key":"11_CR43","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: NeurIPS, vol. 35, pp. 24824\u201324837 (2022)","DOI":"10.52202\/068431-1800"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Xie, X., Bhatnagar, B.L., Pons-Moll, G.: CHORE: contact, human and object reconstruction from a single RGB image. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20086-1_8"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Xie, X., Bhatnagar, B.L., Pons-Moll, G.: Visibility aware human-object interaction tracking from single RGB camera. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00461"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: VITPose: simple vision transformer baselines for human pose estimation. In: NeurIPS, vol. 35, pp. 38571\u201338584 (2022)","DOI":"10.52202\/068431-2795"},{"key":"11_CR47","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint: arXiv:2505.09388 (2025)"},{"key":"11_CR48","unstructured":"Yang, X., et al.: SAM 3D body: robust full-body human mesh recovery. arXiv preprint; identifier to be added (2025)"},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Ye, V., Pavlakos, G., Malik, J., Kanazawa, A.: Decoupling human and camera motion from videos in the wild. In: CVPR, pp. 21222\u201321232 (2023)","DOI":"10.1109\/CVPR52729.2023.02033"},{"key":"11_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: EgoBody: human body shape and motion of interacting people from head-mounted devices. In: ECCV, pp. 180\u2013200. Springer (2022)","DOI":"10.1007\/978-3-031-20068-7_11"},{"key":"11_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Li, A., Tang, Y., Zhao, W., Zhou, J., Lu, J.: DPMesh: exploiting diffusion prior for occluded human mesh recovery. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00111"}],"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\/978-3-032-36984-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:57:39Z","timestamp":1790276259000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36984-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369833","9783032369840"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36984-0_11","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":"25 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"}}]}}