{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:08:16Z","timestamp":1789373296813,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372543","type":"print"},{"value":"9783032372550","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\/978-3-032-37255-0_19","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T07:57:59Z","timestamp":1789372679000},"page":"344-361","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VoxAnchor: Explicit Voxel-Semantic Grounding for\u00a0Spatial Understanding in\u00a0Videos"],"prefix":"10.1007","author":[{"given":"Xinglin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"TingTing","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingzhi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuxuan","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"19_CR1","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"19_CR2","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. ArXiv abs\/2502.13923 (2025). https:\/\/api.semanticscholar.org\/CorpusID:276449796"},{"key":"19_CR3","unstructured":"Cao, M., Li, X., Liu, X., Reid, I., Liang, X.: SpatialDreamer: incentivizing spatial reasoning via active mental imagery. arXiv preprint arXiv:2512.07733 (2025)"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: SpatialVLM: endowing vision-language models with spatial reasoning capabilities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14455\u201314465 (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"19_CR5","unstructured":"Chen, Y., Qi, Z., Zhang, W., Jin, X., Zhang, L., Liu, P.: Reasoning in space via grounding in the world (2025). https:\/\/arxiv.org\/abs\/2510.13800"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T.A., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2432\u20132443 (2017). https:\/\/api.semanticscholar.org\/CorpusID:7684883","DOI":"10.1109\/CVPR.2017.261"},{"key":"19_CR7","unstructured":"Dehghan, A., et al.: ARKitScenes: a diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data. In: NeurIPS Datasets and Benchmarks (2021). https:\/\/api.semanticscholar.org\/CorpusID:237277377"},{"key":"19_CR8","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Neural Information Processing Systems (2014). https:\/\/api.semanticscholar.org\/CorpusID:2255738"},{"key":"19_CR9","unstructured":"Epstein, R.A., Baker, C.I.: Scene perception in the human brain. Ann. Rev. Vision Sci. (2019). https:\/\/api.semanticscholar.org\/CorpusID:195260816"},{"key":"19_CR10","unstructured":"Fan, Z., et al.: VLM-3R: vision-language models augmented with instruction-aligned 3D reconstruction. ArXiv abs\/2505.20279 (2025). https:\/\/api.semanticscholar.org\/CorpusID:279449925"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Fu, C., et al.: Video-MME: the first-ever comprehensive evaluation benchmark of multi-modal LLMs in video analysis. In: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24108\u201324118 (2024). https:\/\/api.semanticscholar.org\/CorpusID:270199408","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Gibson, J.J.: The Ecological Approach to Visual Perception: Classic Edition (2014). https:\/\/api.semanticscholar.org\/CorpusID:69960436","DOI":"10.4324\/9781315740218"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Godard, C., Aodha, O.M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3827\u20133837 (2018). https:\/\/api.semanticscholar.org\/CorpusID:46936649","DOI":"10.1109\/ICCV.2019.00393"},{"key":"19_CR14","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. ArXiv abs\/2009.03300 (2020). https:\/\/api.semanticscholar.org\/CorpusID:221516475"},{"key":"19_CR15","unstructured":"Hu, W., et al.: G2VLM: geometry grounded vision language model with unified 3D reconstruction and spatial reasoning. ArXiv abs\/2511.21688 (2025). https:\/\/api.semanticscholar.org\/CorpusID:283262189"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Huang, X., Wu, J., Xie, Q., Han, K.: MLLMs need 3D-aware representation supervision for scene understanding. ArXiv abs\/2506.01946 (2025). https:\/\/api.semanticscholar.org\/CorpusID:279119197","DOI":"10.52202\/085713-2282"},{"key":"19_CR17","unstructured":"Hurst, A., et al.: GPT-4o system card (2024). arXiv preprint arXiv:2410.21276"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Karaev, N., Rocco, I., Graham, B., Neverova, N., Vedaldi, A., Rupprecht, C.: CoTracker: it is better to track together. In: Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, 29 September\u20134 October 2024, Proceedings, Part LXII. LNCSc, vol. 15120, pp. 18\u201335 (2024)","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimkuehler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. (TOG) 42, 1\u201314 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259267917","DOI":"10.1145\/3592433"},{"key":"19_CR20","unstructured":"Li, B., et al.: LLaVA-OneVision: easy visual task transfer. ArXiv abs\/2408.03326 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271719914"},{"key":"19_CR21","unstructured":"Li, H., et al.: IGGT: instance-grounded geometry transformer for semantic 3D reconstruction (2025). https:\/\/arxiv.org\/abs\/2510.22706"},{"key":"19_CR22","unstructured":"Lin, B., Zhu, B., Ye, Y., Ning, M., Jin, P., Yuan, L.: Video-LLaVa: learning united visual representation by alignment before projection. ArXiv abs\/2311.10122 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265281544"},{"key":"19_CR23","unstructured":"Lin, H., et al.: Depth anything 3: recovering the visual space from any views. ArXiv abs\/2511.10647 (2025). https:\/\/api.semanticscholar.org\/CorpusID:282992334"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Lin, J., et al.: VILA: on pre-training for visual language models. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26679\u201326689 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266174746","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"19_CR25","unstructured":"Liu, Z., Du, Y., Fu, T., Su, S., Ho, C., Wang, C.: Vision-language memory for spatial reasoning. ArXiv abs\/2511.20644 (2025). https:\/\/api.semanticscholar.org\/CorpusID:283251433"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Malcolm, G.L., Groen, I.I.A., Baker, C.I.: Making sense of real-world scenes. Trends Cogn. Sci. 20 11, 843\u2013856 (2016). https:\/\/api.semanticscholar.org\/CorpusID:3682956","DOI":"10.1016\/j.tics.2016.09.003"},{"key":"19_CR27","unstructured":"Marr, D.: Vision: A Computational Investigation into the Human Representation and Processing of Visual Information (1983). https:\/\/api.semanticscholar.org\/CorpusID:267799236"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: European Conference on Computer Vision (2020). https:\/\/api.semanticscholar.org\/CorpusID:221112099","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"19_CR29","unstructured":"Ravi, N., et al.: SAM 2: segment anything in images and videos. In: The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, 24\u201328 April 2025 (2025)"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S.M., et al.: Scene representation transformer: geometry-free novel view synthesis through set-latent scene representations. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6219\u20136228 (2021). https:\/\/api.semanticscholar.org\/CorpusID:244709599","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4104\u20134113 (2016). https:\/\/api.semanticscholar.org\/CorpusID:1728538","DOI":"10.1109\/CVPR.2016.445"},{"key":"19_CR32","unstructured":"Team, G., et al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context (2024). arXiv preprint arXiv:2403.05530"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotn\u00fd, D.: VGGT: visual geometry grounded transformer. In: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5294\u20135306 (2025). https:\/\/api.semanticscholar.org\/CorpusID:277043968","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Holynski, A., Efros, A.A., Kanazawa, A.: Continuous 3D perception model with persistent state. In: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10510\u201310522 (2025). https:\/\/api.semanticscholar.org\/CorpusID:275789153","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: DUSt3R: geometric 3D vision made easy. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20697\u201320709 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266436038","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"19_CR36","unstructured":"Wang, W., et al.: InternVL3. 5: advancing open-source multimodal models in versatility, reasoning, and efficiency (2025). arXiv preprint arXiv:2508.18265"},{"key":"19_CR37","unstructured":"Wang, Y., et al.: $$\\pi ^3$$: permutation-equivariant visual geometry learning (2025). https:\/\/arxiv.org\/abs\/2507.13347"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Wu, D., Liu, F., Hung, Y.H., Duan, Y.: Spatial-MLLM: boosting MLLM capabilities in visual-based spatial intelligence (2025). arXiv preprint arXiv:2505.23747","DOI":"10.52202\/085713-0457"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Wu, G., et al.: 4D Gaussian splatting for real-time dynamic scene rendering. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20310\u201320320 (2023). https:\/\/api.semanticscholar.org\/CorpusID:263908793","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Point transformer V3: simpler, faster, stronger. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4840\u20134851 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266335894","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Yang, J., Yang, S., Gupta, A.W., Han, R., Fei-Fei, L., Xie, S.: Thinking in space: how multimodal large language models see, remember, and recall spaces. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10632\u201310643 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"19_CR42","unstructured":"Yang, R., et\u00a0al.: Visual spatial tuning. arXiv preprint arXiv:2511.05491 (2025)"},{"key":"19_CR43","unstructured":"Yang, S., et al.: Cambrian-S: towards spatial supersensing in video. ArXiv abs\/2511.04670 (2025). https:\/\/api.semanticscholar.org\/CorpusID:282812799"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Ye, M., Danelljan, M., Yu, F., Ke, L.: Gaussian grouping: segment and edit anything in 3D scenes. In: European Conference on Computer Vision (2023). https:\/\/api.semanticscholar.org\/CorpusID:265551523","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"19_CR45","doi-asserted-by":"crossref","unstructured":"Yeshwanth, C., Liu, Y.C., Nie\u00dfner, M., Dai, A.: ScanNet++: a high-fidelity dataset of 3D indoor scenes. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12\u201322 (2023). https:\/\/api.semanticscholar.org\/CorpusID:261064784","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"19_CR46","unstructured":"Yin, B., et\u00a0al.: Spatial mental modeling from limited views. In: Structural Priors for Vision Workshop at ICCV 2025 (2025)"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Yue, X., ET AL.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. iN: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9556\u20139567 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265466525","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"19_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-LLaMA: an instruction-tuned audio-visual language model for video understanding. In: Conference on Empirical Methods in Natural Language Processing (2023). https:\/\/api.semanticscholar.org\/CorpusID:259075356","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"19_CR49","unstructured":"Zhang, Y., et al.: LLaVA-Next: a strong zero-shot video understanding model (2024). https:\/\/llava-vl.github.io\/blog\/2024-04-30-llava-next-video\/"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Zheng, D., Huang, S., Li, Y., Wang, L.: Learning from videos for 3D world: enhancing MLLMs with 3D vision geometry priors. ArXiv abs\/2505.24625 (2025). https:\/\/api.semanticscholar.org\/CorpusID:279070749","DOI":"10.52202\/085713-0693"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: Feature 3DGS: supercharging 3D Gaussian splatting to enable distilled feature fields. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21676\u201321685 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265722936","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"19_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M.A., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6612\u20136619 (2017). https:\/\/api.semanticscholar.org\/CorpusID:11977588","DOI":"10.1109\/CVPR.2017.700"}],"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\/978-3-032-37255-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T07:58:31Z","timestamp":1789372711000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37255-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372543","9783032372550"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37255-0_19","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":"15 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"}}]}}