{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:10:55Z","timestamp":1789038655575,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":89,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373922","type":"print"},{"value":"9783032373939","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\/978-3-032-37393-9_16","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:40:22Z","timestamp":1789036822000},"page":"255-274","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Language: Grounding Referring Expressions with\u00a0Hand Pointing in\u00a0Egocentric Vision"],"prefix":"10.1007","author":[{"given":"Ling","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zinuo","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Jie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhui","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenglun","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhidong","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"16_CR1","unstructured":"Achiam, J., et al.: GPT-4 Technical Report. ArXiv Preprint: ArXiv:2303.08774 (2023)"},{"key":"16_CR2","unstructured":"Ahuja, C.: Communication Beyond Words: Grounding Visual Body Motion with Language. Ph.D. thesis, Carnegie Mellon University (2022)"},{"key":"16_CR3","unstructured":"An, X., et al.: LLaVA-onevision-1.5: fully open framework for democratized multimodal training. ArXiv Preprint: ArXiv:2509.23661 (2025)"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3674\u20133683 (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"16_CR6","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. ArXiv Preprint: ArXiv:2309.16609 (2023)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Bansal, S., Arora, C., Jawahar, C.: My view is the best view: procedure learning from egocentric videos. In: Proceedings of the European Conference on Computer Vision, pp. 657\u2013675 (2022)","DOI":"10.1007\/978-3-031-19778-9_38"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Bhattacharyya, P., et al.: Helios: an extremely low power event-based gesture recognition for always-on smart eyewear. In: European Conference on Computer Vision, pp. 168\u2013184. Springer (2024)","DOI":"10.1007\/978-3-031-91989-3_11"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Chandel, H., Vatta, S.: Occlusion detection and handling: a review. Int. J. Comput. Appl. 120 (2015)","DOI":"10.5120\/21264-3857"},{"key":"16_CR10","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal LLM\u2019s referential dialogue magic. ArXiv Preprint: ArXiv:2306.15195 (2023)"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Chen, W., Chen, L., Wu, Y.: An efficient and effective transformer decoder-based framework for multi-task visual grounding. In: European Conference on Computer Vision, pp. 125\u2013141. Springer (2024)","DOI":"10.1007\/978-3-031-72995-9_8"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: YouRefIt: embodied reference understanding with language and gesture. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1385\u20131395 (2021)","DOI":"10.1109\/ICCV48922.2021.00142"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, P., Ma, L., Wong, K.Y.K., Wu, Q.: Cops-ref: a new dataset and task on compositional referring expression comprehension. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10086\u201310095 (2020)","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, T., Song, L., Ge, Y., Liu, W., Wang, X., Shan, Y.: YOLO-world: real-time open-vocabulary object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16901\u201316911 (2024)","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"16_CR15","unstructured":"Chuang, Y.S., et al.: Meta CLIP 2: a worldwide scaling recipe.. ArXiv Preprint: ArXiv:2507.22062 (2025)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Constantin, S., Eyiokur, F.I., Yaman, D., B\u00e4rmann, L., Waibel, A.: Interactive multimodal robot dialog using pointing gesture recognition. In: European Conference on Computer Vision, pp. 640\u2013657. Springer (2022)","DOI":"10.1007\/978-3-031-25075-0_43"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Dai, M., Yang, L., Xu, Y., Feng, Z., Yang, W.: SimVG: a simple framework for visual grounding with decoupled multi-modal fusion. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 121670\u2013121698 (2024)","DOI":"10.52202\/079017-3867"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"De Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., Courville, A.: GuessWhat?! Visual object discovery through multi-modal dialogue. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5503\u20135512 (2017)","DOI":"10.1109\/CVPR.2017.475"},{"key":"16_CR19","unstructured":"Deichler, A., O\u2019Regan, J., Beskow, J.: MM-conv: a multi-modal conversational dataset for virtual humans. arXiv preprint: arXiv:2410.00253 (2024)"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Delmas, G., Weinzaepfel, P., Moreno-Noguer, F., Rogez, G.: PoseEmbroider: towards a 3D, visual, semantic-aware human pose representation. In: European Conference on Computer Vision, pp. 55\u201373. Springer (2024)","DOI":"10.1007\/978-3-031-73209-6_4"},{"key":"16_CR21","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TETCI.2022.3141105","volume":"6","author":"J Duan","year":"2022","unstructured":"Duan, J., Yu, S., Tan, H.L., Zhu, H., Tan, C.: A survey of embodied AI: from simulators to research tasks. IEEE Trans. Emerg. Top. Comput. Intell. 6, 230\u2013244 (2022)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Efron, R.: What is perception? In: Proceedings of the Boston Colloquium for the Philosophy of Science 1966\/1968, pp. 137\u2013173 (1969)","DOI":"10.1007\/978-94-010-3378-7_4"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Fan, Z., et\u00a0al.: Benchmarks and challenges in pose estimation for egocentric hand interactions with objects. In: European Conference on Computer Vision, pp. 428\u2013448. Springer (2024)","DOI":"10.1007\/978-3-031-72698-9_25"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Farkhondeh, A., Tafasca, S., Odobez, J.M.: ChildPlay-hand: a dataset of hand manipulations in the wild. In: European Conference on Computer Vision, pp. 101\u2013118. Springer (2024)","DOI":"10.1007\/978-3-031-91578-9_6"},{"issue":"1","key":"16_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/stul.12221","volume":"78","author":"J Fortuny","year":"2024","unstructured":"Fortuny, J., Payrat\u00f3, L.: Ambiguity in linguistics. Studia Linguistica 78(1), 1\u20137 (2024)","journal-title":"Studia Linguistica"},{"key":"16_CR26","unstructured":"Foteinos, K., Angelidis, G., Psiris, A., Argyriou, V., Sarigiannidis, P., Papadopoulos, G.T.: FR-GESTURE: an RGBD dataset for gesture-based human-robot interaction in first responder operations. arXiv preprint: arXiv:2602.17573 (2026)"},{"key":"16_CR27","unstructured":"Gao, Y., et\u00a0al.: Seedream 3.0 technical report. ArXiv Preprint: ArXiv:2504.11346 (2025)"},{"key":"16_CR28","unstructured":"Grauman, K., et\u00a0al.: Ego4D: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18995\u201319012 (2022)"},{"key":"16_CR29","unstructured":"Grauman, K., et al.: Ego-Exo4D: understanding skilled human activity from first- and third-person perspectives. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19383\u201319400 (2024)"},{"key":"16_CR30","unstructured":"Guo, D., et\u00a0al.: Seed1. 5-Vl technical report. ArXiv Preprint: ArXiv:2505.07062 (2025)"},{"key":"16_CR31","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1109\/THMS.2021.3086003","volume":"51","author":"L Guo","year":"2021","unstructured":"Guo, L., Lu, Z., Yao, L.: Human-machine interaction sensing technology based on hand gesture recognition: a review. IEEE Trans. Hum.-Mach. Syst. 51, 300\u2013309 (2021)","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"key":"16_CR32","doi-asserted-by":"publisher","first-page":"143599","DOI":"10.1109\/ACCESS.2024.3421992","volume":"12","author":"AO Hashi","year":"2024","unstructured":"Hashi, A.O., Hashim, S.Z.M., Asamah, A.B.: A systematic review of hand gesture recognition: an update from 2018 to 2024. IEEE Access 12, 143599\u2013143626 (2024)","journal-title":"IEEE Access"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Da, H., Miura, N.L., Hayashi, J., K.: Enhancing human-robot collaborative search through efficient space sharing with on-demand bidirectional interaction. In: European Conference on Computer Vision, pp. 20\u201335. Springer (2024)","DOI":"10.1007\/978-3-031-92591-7_2"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Huang, Z., Satoh, S.: LoA-trans: enhancing visual grounding by location-aware transformers. In: European Conference on Computer Vision, pp. 405\u2013421. Springer (2024)","DOI":"10.1007\/978-3-031-72667-5_23"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Hummel, T., Karthik, S., Georgescu, M.I., Akata, Z.: EgoCVR: an egocentric benchmark for fine-grained composed video retrieval. In: European Conference on Computer Vision, pp. 1\u201317. Springer (2024)","DOI":"10.1007\/978-3-031-72913-3_1"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Jiang, H., Lu, Z.: Visual grounding for object-level generalization in reinforcement learning. In: European Conference on Computer Vision, pp. 55\u201372. Springer (2024)","DOI":"10.1007\/978-3-031-73404-5_4"},{"issue":"7","key":"16_CR37","doi-asserted-by":"publisher","first-page":"2297","DOI":"10.1007\/s00521-020-05109-w","volume":"33","author":"D Jirak","year":"2021","unstructured":"Jirak, D., Biertimpel, D., Kerzel, M., Wermter, S.: Solving visual object ambiguities when pointing: an unsupervised learning approach. Neural Comput. Appl. 33(7), 2297\u20132319 (2021)","journal-title":"Neural Comput. Appl."},{"key":"16_CR38","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, pp. 222\u2013239. Springer (2024)","DOI":"10.1007\/978-3-031-72940-9_13"},{"key":"16_CR39","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":"16_CR40","doi-asserted-by":"crossref","unstructured":"Kang, W., Liu, G., Shah, M., Yan, Y.: SegVG: transferring object bounding box to segmentation for visual grounding. In: European Conference on Computer Vision, pp. 57\u201375. Springer (2024)","DOI":"10.1007\/978-3-031-72920-1_4"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferItGame: referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Kusnanti, E.A., Sierra, E., Putra, G.G.S., Cahyadi, E.S., Haq, A., Purwitasari, D.: Indonesian lexical ambiguity in machine translation: a literature review. In: 2024 International Conference on Information Technology Research and Innovation (ICITRI), pp. 59\u201364. IEEE (2024)","DOI":"10.1109\/ICITRI62858.2024.10698991"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Lee, J., Wang, J., Brown, E., Chu, L., Rodriguez, S.S., Froehlich, J.E.: GazePointAR: a context-aware multimodal voice assistant for pronoun disambiguation in wearable augmented reality. In: Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, pp. 1\u201320 (2024)","DOI":"10.1145\/3613904.3642230"},{"key":"16_CR44","unstructured":"Li, H., Wang, Y., Hao, W., Zhang, P., Wang, D., Lu, H.: RAGTrack: language-aware RGBT tracking with retrieval-augmented generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28179\u201328189 (2026)"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: CADTrack: learning contextual aggregation with deformable alignment for robust RGBT tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a040, pp. 6109\u20136117 (2026)","DOI":"10.1609\/aaai.v40i8.37535"},{"key":"16_CR46","unstructured":"Li, L., et al.: From sparse to dense: spatio-temporal fusion for multi-view 3D human pose estimation with DenseWarper. arXiv preprint: arXiv:2605.14525 (2026)"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Li, L., Gu, R., Wang, C., Xing, J., Yu, X., Zhang, X.P.: Multi-view 3D human pose estimation with weakly synchronized images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 4833\u20134841 (2025)","DOI":"10.1609\/aaai.v39i5.32511"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Li, L., Yang, W., Yu, X., Xing, J., Zhang, X.P.: Translating motion to notation: Hand labanotation for intuitive and comprehensive hand movement documentation. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 4092\u20134100 (2024)","DOI":"10.1145\/3664647.3680568"},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Li, Z., et\u00a0al.: GroundingGPT: language enhanced multi-modal grounding model. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pp. 6657\u20136678 (2024)","DOI":"10.18653\/v1\/2024.acl-long.360"},{"key":"16_CR50","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Proceedings of the European Conference on Computer Vision, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"16_CR51","unstructured":"Linderman, G.C., Rachh, M., Hoskins, J.G., Steinerberger, S., Kluger, Y.: Efficient algorithms for t-distributed stochastic neighborhood embedding. ArXiv Preprint: ArXiv:1712.09005 (2017)"},{"key":"16_CR52","unstructured":"Liu, A., et al.: DeepSeek-V3 technical report. ArXiv Preprint: ArXiv:2412.19437 (2024)"},{"key":"16_CR53","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"16_CR54","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: AerialVG: a challenging benchmark for aerial visual grounding by exploring positional relations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5177\u20135187 (2025)","DOI":"10.1109\/ICCV51701.2025.00492"},{"key":"16_CR55","doi-asserted-by":"crossref","unstructured":"Liu, R., Liu, C., Bai, Y., Yuille, A.L.: CLEVR-Ref+: diagnosing visual reasoning with referring expressions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4185\u20134194 (2019)","DOI":"10.1109\/CVPR.2019.00431"},{"key":"16_CR56","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: Proceedings of the European Conference on Computer Vision, pp. 38\u201355 (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"16_CR57","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Aligning cyber space with physical world: a comprehensive survey on embodied AI. IEEE\/ASME Trans. Mechatron., 1\u201322 (2025)","DOI":"10.1109\/TMECH.2025.3574943"},{"key":"16_CR58","doi-asserted-by":"crossref","unstructured":"Magay, A., Tripathi, D., Hao, Y., Fang, Y.: A light and smart wearable platform with multimodal foundation model for enhanced spatial reasoning in people with blindness and low vision. In: European Conference on Computer Vision, pp. 323\u2013339. Springer (2024)","DOI":"10.1007\/978-3-031-92591-7_20"},{"key":"16_CR59","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"16_CR60","doi-asserted-by":"crossref","unstructured":"Memmi, M.Y., Slama, R., Berretti, S.: Hand gesture recognition using dual graph hierarchical edges representation and graph transformer network. In: European Conference on Computer Vision, pp. 53\u201368. Springer (2024)","DOI":"10.1007\/978-3-031-92591-7_4"},{"key":"16_CR61","unstructured":"Mo, M., et al.: NexusAD: exploring the nexus for multimodal perception and comprehension of corner cases in autonomous driving. In: ECCV 2024 Workshop on Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving (2024)"},{"key":"16_CR62","doi-asserted-by":"crossref","unstructured":"Nagaraja, V.K., Morariu, V.I., Davis, L.S.: Modeling context between objects for referring expression understanding. In: Proceedings of the European Conference on Computer Vision, pp. 792\u2013807 (2016)","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"16_CR63","doi-asserted-by":"crossref","unstructured":"Pfeifer, R., Iida, F.: Embodied artificial intelligence: trends and challenges. Lect. Notes Comput. Sci., 1\u201326 (2004)","DOI":"10.1007\/978-3-540-27833-7_1"},{"key":"16_CR64","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"16_CR65","doi-asserted-by":"crossref","unstructured":"Qi, Z., et al.: ShapeLLM: universal 3D object understanding for embodied interaction. In: European Conference on Computer Vision, pp. 214\u2013238. Springer (2024)","DOI":"10.1007\/978-3-031-72775-7_13"},{"key":"16_CR66","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"16_CR67","doi-asserted-by":"crossref","unstructured":"Schauerte, B., Fink, G.A.: Focusing computational visual attention in multi-modal human-robot interaction. In: Proceedings of the International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interaction, pp. 1\u20138 (2010)","DOI":"10.1145\/1891903.1891912"},{"key":"16_CR68","doi-asserted-by":"crossref","unstructured":"Schauerte, B., Richarz, J., Fink, G.A.: Saliency-based identification and recognition of pointed-at objects. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 4638\u20134643 (2010)","DOI":"10.1109\/IROS.2010.5649430"},{"key":"16_CR69","doi-asserted-by":"crossref","unstructured":"Shi, C., Yang, S.: Spatial and visual perspective-taking via view rotation and relation reasoning for embodied reference understanding. In: European Conference on Computer Vision, pp. 201\u2013218. Springer (2022)","DOI":"10.1007\/978-3-031-20059-5_12"},{"key":"16_CR70","doi-asserted-by":"crossref","unstructured":"Shukla, D., Erkent, O., Piater, J.: Probabilistic detection of pointing directions for human-robot interaction. In: Proceedings of the 2015 International Conference on Digital Image Computing: Techniques and Applications, pp. 1\u20138 (2015)","DOI":"10.1109\/DICTA.2015.7371296"},{"key":"16_CR71","doi-asserted-by":"crossref","unstructured":"Shukla, D., Erkent, \u00d6., Piater, J.: A Multi-view hand gesture RGB-D dataset for human-robot interaction scenarios. In: Proceedings of the IEEE International Symposium on Robot and Human Interactive Communication, pp. 1084\u20131091 (2016)","DOI":"10.1109\/ROMAN.2016.7745243"},{"key":"16_CR72","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint: arXiv:2312.11805 (2023)"},{"key":"16_CR73","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1038\/s41433-023-02842-z","volume":"38","author":"E Waisberg","year":"2024","unstructured":"Waisberg, E., et al.: Meta smart glasses\u2014large language models and the future for assistive glasses for individuals with vision impairments. Eye 38, 1036\u20131038 (2024)","journal-title":"Eye"},{"key":"16_CR74","unstructured":"Wang, G., et al.: Voyager: an open-ended embodied agent with large language models. ArXiv Preprint: ArXiv:2305.16291 (2023)"},{"key":"16_CR75","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. ArXiv Preprint: ArXiv:2409.12191 (2024)"},{"key":"16_CR76","unstructured":"Wang, W., et al.: InternVL3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency. ArXiv Preprint: ArXiv:2508.18265 (2025)"},{"issue":"7","key":"16_CR77","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1167\/2.7.435","volume":"2","author":"K Watanabe","year":"2002","unstructured":"Watanabe, K.: Reflexive attentional shift caused by indexical pointing gesture. J. Vis. 2(7), 435\u2013435 (2002)","journal-title":"J. Vis."},{"key":"16_CR78","unstructured":"Wu, Z., et\u00a0al.: DeepSeek-VL2: mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint: arXiv:2412.10302 (2024)"},{"key":"16_CR79","doi-asserted-by":"crossref","unstructured":"Xiao, B., et al.: Florence-2: advancing a unified representation for a variety of vision tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4818\u20134829 (2024)","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"16_CR80","doi-asserted-by":"crossref","unstructured":"Xiao, L., Yang, X., Lan, X., Wang, Y., Xu, C.: Towards visual grounding: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3630635"},{"key":"16_CR81","doi-asserted-by":"crossref","unstructured":"Xiao, L., Yang, X., Peng, F., Wang, Y., Xu, C.: OneRef: unified one-tower expression grounding and segmentation with mask referring modeling. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 139854\u2013139885 (2024)","DOI":"10.52202\/079017-4438"},{"key":"16_CR82","doi-asserted-by":"crossref","unstructured":"Xie, P., Chen, S., Dai, Y., Hu, D., Yang, K., Wang, G.: Target-oriented object grasping via multimodal human guidance. In: European Conference on Computer Vision, pp. 305\u2013322. Springer (2024)","DOI":"10.1007\/978-3-031-92591-7_19"},{"key":"16_CR83","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. ArXiv Preprint: ArXiv:2505.09388 (2025)"},{"key":"16_CR84","doi-asserted-by":"crossref","unstructured":"Yang, J., Ding, R., Brown, E., Qi, X., Xie, S.: V-IRL: grounding virtual intelligence in real life. In: European Conference on Computer Vision, pp. 36\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72995-9_3"},{"key":"16_CR85","unstructured":"You, H., et al.: Ferret: refer and ground anything anywhere at any granularity. ArXiv Preprint: ArXiv:2310.07704 (2023)"},{"key":"16_CR86","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Proceedings of the European Conference on Computer Vision, pp. 69\u201385 (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"16_CR87","doi-asserted-by":"crossref","unstructured":"Zhang, H., Niu, Y., Chang, S.F.: Grounding referring expressions in images by variational context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4158\u20134166 (2018)","DOI":"10.1109\/CVPR.2018.00437"},{"key":"16_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, H., et\u00a0al.: LLaVA-grounding: grounded visual chat with large multimodal models. In: Proceedings of the European Conference on Computer Vision, pp. 19\u201335 (2024)","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"16_CR89","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Wu, Q., Shen, C., Reid, I., Van Den Hengel, A.: Parallel attention: a unified framework for visual object discovery through dialogs and queries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4252\u20134261 (2018)","DOI":"10.1109\/CVPR.2018.00447"}],"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\/978-3-032-37393-9_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:40:56Z","timestamp":1789036856000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37393-9_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373922","9783032373939"],"references-count":89,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37393-9_16","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"}}]}}