{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T19:40:28Z","timestamp":1783021228750,"version":"3.54.6"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032045546","type":"print"},{"value":"9783032045553","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"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\/978-3-032-04555-3_26","type":"book-chapter","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T08:56:24Z","timestamp":1757580984000},"page":"314-325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ViSMoE: Visual-Aware Sparse Mixture-of-Experts for\u00a0Embodied Referring Expression Grounding"],"prefix":"10.1007","author":[{"given":"Shuo","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piji","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"26_CR1","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":"26_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: EVE: efficient vision-language pre-training with masked prediction and modality-aware MoE. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 1110\u20131119 (2024)","DOI":"10.1609\/aaai.v38i2.27872"},{"key":"26_CR3","first-page":"5834","volume":"34","author":"S Chen","year":"2021","unstructured":"Chen, S., Guhur, P.L., Schmid, C., Laptev, I.: History aware multimodal transformer for vision-and-language navigation. Adv. Neural. Inf. Process. Syst. 34, 5834\u20135847 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Chen, S., Guhur, P.L., Tapaswi, M., Schmid, C., Laptev, I.: Think global, act local: dual-scale graph transformer for vision-and-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16537\u201316547 (2022)","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., et al.: AdaMV-MoE: adaptive multi-task vision mixture-of-experts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17346\u201317357 (2023)","DOI":"10.1109\/ICCV51070.2023.01591"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Gao, C., Chen, J., Liu, S., Wang, L., Zhang, Q., Wu, Q.: Room-and-object aware knowledge reasoning for remote embodied referring expression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3064\u20133073 (2021)","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"26_CR7","unstructured":"Gupta, S., et al.: Sparsely activated mixture-of-experts are robust multi-task learners. arXiv preprint arXiv:2204.07689 (2022)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Si, C., Lu, Z., Huang, Y., Wang, L., Wang, X.: Frequency-enhanced data augmentation for vision-and-language navigation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.52202\/075280-0193"},{"issue":"1","key":"26_CR9","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991)","journal-title":"Neural Comput."},{"issue":"2","key":"26_CR10","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1162\/neco.1994.6.2.181","volume":"6","author":"MI Jordan","year":"1994","unstructured":"Jordan, M.I., Jacobs, R.A.: Hierarchical mixtures of experts and the EM algorithm. Neural Comput. 6(2), 181\u2013214 (1994)","journal-title":"Neural Comput."},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, Z., Yang, J., Wang, Y., Jiang, S.: KERM: knowledge enhanced reasoning for vision-and-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2583\u20132592 (2023)","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"26_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Lin, X., Li, G., Yu, Y.: Scene-intuitive agent for remote embodied visual grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7036\u20137045 (2021)","DOI":"10.1109\/CVPR46437.2021.00696"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Mohammadi, B., Hong, Y., Qi, Y., Wu, Q., Pan, S., Shi, J.Q.: Augmented commonsense knowledge for remote object grounding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 4269\u20134277 (2024)","DOI":"10.1609\/aaai.v38i5.28223"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Qi, Y., et al.: Reverie: remote embodied visual referring expression in real indoor environments. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9982\u20139991 (2020)","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"26_CR16","unstructured":"Ross, S., Gordon, G., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 627\u2013635. JMLR Workshop and Conference Proceedings (2011)"},{"key":"26_CR17","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: Lxmert: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"26_CR19","unstructured":"Vaswani, A.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Wang, A.: Glue: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, X., Yang, J., Liu, Y., Jiang, S.: Gridmm: grid memory map for vision-and-language navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15625\u201315636 (2023)","DOI":"10.1109\/ICCV51070.2023.01432"},{"issue":"8","key":"26_CR22","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1109\/TNNLS.2012.2200299","volume":"23","author":"SE Yuksel","year":"2012","unstructured":"Yuksel, S.E., Wilson, J.N., Gader, P.D.: Twenty years of mixture of experts. IEEE Trans. Neural Netw. Learn. Syst. 23(8), 1177\u20131193 (2012)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: Target-driven structured transformer planner for vision-language navigation. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4194\u20134203 (2022)","DOI":"10.1145\/3503161.3548281"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, F., Liang, X., Zhu, Y., Yu, Q., Chang, X., Liang, X.: Soon: scenario oriented object navigation with graph-based exploration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12689\u201312699 (2021)","DOI":"10.1109\/CVPR46437.2021.01250"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04555-3_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T18:47:35Z","timestamp":1783018055000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04555-3_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"ISBN":["9783032045546","9783032045553"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04555-3_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"12 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}