{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T12:07:42Z","timestamp":1789042062016,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370198","type":"print"},{"value":"9783032370204","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\/978-3-032-37020-4_38","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:13:54Z","timestamp":1789038834000},"page":"699-715","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SWAN: World-Aware Adaptive Multimodal Networks for\u00a0Runtime Variations"],"prefix":"10.1007","author":[{"given":"Jason","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shir-Kang Scott","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maggie","family":"Wigness","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lance M.","family":"Kaplan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mani","family":"Srivastava","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","unstructured":"Bai, X., et al.: Transfusion: Robust lidar-camera fusion for 3d object detection with transformers (2022). https:\/\/arxiv.org\/abs\/2203.11496","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Beemelmanns, T., Zhang, Q., Geller, C., Eckstein, L.: Multicorrupt: A multi-modal robustness dataset and benchmark of lidar-camera fusion for 3d object detection. In: 2024 IEEE Intelligent Vehicles Symposium (IV), pp. 3255\u20133261. IEEE (2024)","DOI":"10.1109\/IV55156.2024.10588664"},{"key":"38_CR3","unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)"},{"key":"38_CR4","unstructured":"Bolukbasi, T., Wang, J., Dekel, O., Saligrama, V.: Adaptive neural networks for fast test-time prediction. arXiv preprint arXiv:1702.078111(3) (2017)"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: A multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"38_CR6","unstructured":"Cai, H., Gan, C., Wang, T., Zhang, Z., Han, S.: Once-for-all: Train one network and specialize it for efficient deployment. arXiv preprint arXiv:1908.09791 (2019)"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhang, T., Wang, Y., Wang, Y., Zhao, H.: Futr3d: A unified sensor fusion framework for 3d detection. In: proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 172\u2013181 (2023)","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"38_CR8","unstructured":"Fan, A., Grave, E., Joulin, A.: Reducing transformer depth on demand with structured dropout. arXiv preprint arXiv:1909.11556 (2019)"},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Fan, L., et al.: Embracing single stride 3d object detector with sparse transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8458\u20138468 (2022)","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"38_CR10","unstructured":"Grover, A., Wang, E., Zweig, A., Ermon, S.: Stochastic optimization of sorting networks via continuous relaxations. arXiv preprint arXiv:1903.08850 (2019)"},{"key":"38_CR11","unstructured":"Hu, B., Xu, L., Moon, J., Yadwadkar, N.J., Akella, A.: Mosel: Inference serving using dynamic modality selection (2023). https:\/\/arxiv.org\/abs\/2310.18481"},{"key":"38_CR12","unstructured":"Huang, G., Chen, D., Li, T., Wu, F., Van Der Maaten, L., Weinberger, K.Q.: Multi-scale dense networks for resource efficient image classification. arXiv preprint arXiv:1703.09844 (2017)"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Ji, M., Zhang, S., Yang, J.: Depthfusion: Depth-aware hybrid feature fusion for lidar-camera 3d object detection. IEEE Trans. Multimedia (2026)","DOI":"10.1109\/TMM.2026.3668596"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Jing, W., Chen, X., Nie, S., Jiao, Z., Ma, J.: Hd-fusion: Hierarchical dynamic fusion of lidar-camera for robust 3-d object detection. IEEE Trans. Industr. Inf. (2026)","DOI":"10.1109\/TII.2026.3678060"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Li, H., Zhang, H., Qi, X., Yang, R., Huang, G.: Improved techniques for training adaptive deep networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1891\u20131900 (2019)","DOI":"10.1109\/ICCV.2019.00198"},{"key":"38_CR16","unstructured":"Li, Y., Lyu, C., Wang, H.: Freqexit: Enabling early-exit inference for visual autoregressive models via frequency-aware guidance. In: Belgrave, D., et al. (eds.) Advances in Neural Information Processing Systems. vol.\u00a038, pp. 103763\u2013103788. Curran Associates, Inc. (2025). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2025\/file\/95cb60b65d9f2c0cd78b567ffebde9e6-Paper-Conference.pdf"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Liu, L., et al.: Towards accurate and efficient 3d object detection for autonomous driving: A mixture of experts computing system on edge. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 25903\u201325913 (2025)","DOI":"10.1109\/ICCV51701.2025.02403"},{"key":"38_CR18","doi-asserted-by":"publisher","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: Petr: Position embedding transformation for multi-view 3d object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 531\u2013548. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_31","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Bevfusion: Multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 2774\u20132781. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yang, X., Tang, H., Yang, S., Han, S.: Flatformer: Flattened window attention for efficient point cloud transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1200\u20131211 (2023)","DOI":"10.1109\/CVPR52729.2023.00122"},{"key":"38_CR22","unstructured":"Maddison, C.J., Mnih, A., Teh, Y.W.: The concrete distribution: A continuous relaxation of discrete random variables. arXiv preprint arXiv:1611.00712 (2016)"},{"key":"38_CR23","doi-asserted-by":"crossref","unstructured":"Meng, L., et al.: Adavit: Adaptive vision transformers for efficient image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12309\u201312318 (2022)","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"38_CR24","unstructured":"NVIDIA Corporation: NVIDIA TensorRT: High-performance deep learning inference sdk (2024). https:\/\/developer.nvidia.com\/tensorrt, Accessed 04 Mar 2026"},{"key":"38_CR25","doi-asserted-by":"crossref","unstructured":"Panda, R., et al.: Adamml: Adaptive multi-modal learning for efficient video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7576\u20137585 (2021)","DOI":"10.1109\/ICCV48922.2021.00748"},{"key":"38_CR26","first-page":"13937","volume":"34","author":"Y Rao","year":"2021","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: Dynamicvit: Efficient vision transformers with dynamic token sparsification. Adv. Neural. Inf. Process. Syst. 34, 13937\u201313949 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"38_CR27","doi-asserted-by":"crossref","unstructured":"Wu, J., Yuan, Y., Yang, K., Kaplan, L., Srivastava, M.: Admn: A layer-wise adaptive multimodal network for dynamic input noise and compute resources (2025). https:\/\/arxiv.org\/abs\/2502.07862","DOI":"10.52202\/085713-2313"},{"key":"38_CR28","doi-asserted-by":"crossref","unstructured":"Yan, J., et al.: Cross modal transformer: Towards fast and robust 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18268\u201318278 (2023)","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"38_CR29","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Mm-fi: Multi-modal non-intrusive 4d human dataset for versatile wireless sensing. In: Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2023). https:\/\/openreview.net\/forum?id=1uAsASS1th","DOI":"10.52202\/075280-0822"}],"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\/978-3-032-37020-4_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:14:08Z","timestamp":1789038848000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37020-4_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370198","9783032370204"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37020-4_38","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"}}]}}