{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T18:04:23Z","timestamp":1769796263044,"version":"3.49.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032145307","type":"print"},{"value":"9783032145314","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\/978-3-032-14531-4_11","type":"book-chapter","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T05:44:45Z","timestamp":1769751885000},"page":"128-140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ViTFuser: Advancements in\u00a0Global Context Understanding for\u00a0Autonomous Vehicles"],"prefix":"10.1007","author":[{"given":"Atanu","family":"Chatterjee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P.","family":"Ajay Vikram","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aniketh Narayan","family":"Bellala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T.","family":"Naga Tarun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Basavaraj","family":"Talawar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Vani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeny","family":"Rajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,31]]},"reference":[{"key":"11_CR1","unstructured":"Prakash, A., Jaeger, B., Chitta, K.: GitHub repository of TransFuser\u20192022 PAMI. https:\/\/github.com\/autonomousvision\/transfuser. Accessed 15 Mar 2024"},{"key":"11_CR2","doi-asserted-by":"publisher","first-page":"50165","DOI":"10.1109\/ACCESS.2024.3385439","volume":"12","author":"S Alaba","year":"2024","unstructured":"Alaba, S.: Transformer-based optimized multimodal fusion for 3D object detection in autonomous driving. IEEE Access 12, 50165\u201350176 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3385439","journal-title":"IEEE Access"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Chen, D., Koltun, V., Kr\u00e4henb\u00fchl, P.: Learning to drive from a world on rails. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15590\u201315599 (2021)","DOI":"10.1109\/ICCV48922.2021.01530"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Chen, D., Kr\u00e4henb\u00fchl, P.: Learning from all vehicles. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17222\u201317231 (2022)","DOI":"10.1109\/CVPR52688.2022.01671"},{"key":"11_CR5","unstructured":"Chen, D., Zhou, B., Koltun, V., Kr\u00e4henb\u00fchl, P.: Learning by cheating. In: Conference on Robot Learning, pp. 66\u201375. PMLR (2020)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Chen, K., et\u00a0al.: Hybrid task cascade for instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4974\u20134983 (2019)","DOI":"10.1109\/CVPR.2019.00511"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Chitta, K., Prakash, A., Geiger, A.: Neat: neural attention fields for end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15793\u201315803 (2021)","DOI":"10.1109\/ICCV48922.2021.01550"},{"key":"11_CR8","doi-asserted-by":"publisher","first-page":"12878","DOI":"10.1109\/TPAMI.2022.3200245","volume":"45","author":"K Chitta","year":"2022","unstructured":"Chitta, K., Prakash, A., Jaeger, B., Yu, Z., Renz, K., Geiger, A.: Transfuser: imitation with transformer-based sensor fusion for autonomous driving. IEEE Trans. Pattern Anal. Mach. Intell. 45, 12878\u201312895 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Codevilla, F., Miiller, M., L\u00f3pez, A., Koltun, V., Dosovitskiy, A.: End-to-end driving via conditional imitation learning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1\u20139 (2018)","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Codevilla, F., Santana, E., L\u00f3pez, A.M., Gaidon, A.: Exploring the limitations of behavior cloning for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9329\u20139338 (2019)","DOI":"10.1109\/ICCV.2019.00942"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Cui, A., Casas, S., Sadat, A., Liao, R., Urtasun, R.: Lookout: diverse multi-future prediction and planning for self-driving. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 16087\u201316096 (2021)","DOI":"10.1109\/ICCV48922.2021.01580"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11_CR14","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"11_CR15","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: Carla: an open urban driving simulator. In: Conference on Robot Learning, pp. 1\u201316. PMLR (2017)"},{"key":"11_CR16","doi-asserted-by":"publisher","unstructured":"Dutta, P., Sistu, G., Yogamani, S., Galv\u00e1in, E., McDonald, J.: Vit-bevseg: a hierarchical transformer network for monocular birds-eye-view segmentation (2022). https:\/\/doi.org\/10.48550\/arXiv.2205.15667","DOI":"10.48550\/arXiv.2205.15667"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Fadadu, S., et al.: Multi-view fusion of sensor data for improved perception and prediction in autonomous driving. In: 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 3292\u20133300 (2022)","DOI":"10.1109\/WACV51458.2022.00335"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., Chen, Y., Hu, R., Urtasun, R.: Multi-task multi-sensor fusion for 3D object detection. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7337\u20137345 (2019)","DOI":"10.1109\/CVPR.2019.00752"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Man, Y., Gui, L.Y., Wang, Y.X.: Bev-guided multi-modality fusion for driving perception. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21960\u201321969 (2023)","DOI":"10.1109\/CVPR52729.2023.02103"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Prakash, A., Chitta, K., Geiger, A.: Multi-modal fusion transformer for end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7077\u20137087 (2021)","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10428\u201310436 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.M.: The synthia dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3234\u20133243 (2016)","DOI":"10.1109\/CVPR.2016.352"},{"key":"11_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1007\/978-3-030-58592-1_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Sadat","year":"2020","unstructured":"Sadat, A., Casas, S., Ren, M., Wu, X., Dhawan, P., Urtasun, R.: Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 414\u2013430. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_25"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Toromanoff, M., Wirbel, E., Moutarde, F.: End-to-end model-free reinforcement learning for urban driving using implicit affordances. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7151\u20137160 (2020)","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"11_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6000\u20136010 (2017)"},{"key":"11_CR28","unstructured":"Xu, D., Li, H., Wang, Q., Song, Z., Chen, L., Deng, H.: M2da: multi-modal fusion transformer incorporating driver attention for autonomous driving (2024). https:\/\/arxiv.org\/abs\/2403.12552"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Yang, W., et al.: Projecting your view attentively: monocular road scene layout estimation via cross-view transformation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15531\u201315540 (2021)","DOI":"10.1109\/CVPR46437.2021.01528"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Yao, Z., Cao, Y., Zheng, S., Huang, G., Lin, S.: Cross-iteration batch normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12331\u201312340 (2021)","DOI":"10.1109\/CVPR46437.2021.01215"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Liniger, A., Dai, D., Yu, F., Van\u00a0Gool, L.: End-to-end urban driving by imitating a reinforcement learning coach. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15222\u201315232 (2021)","DOI":"10.1109\/ICCV48922.2021.01494"}],"container-title":["Communications in Computer and Information Science","Machine Learning, Image Processing, Network Security and Data Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-14531-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T05:44:50Z","timestamp":1769751890000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-14531-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032145307","9783032145314"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-14531-4_11","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"31 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MIND","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Image Processing, Network Security and Data Sciences","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Goa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mind2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mind2024.mind-society.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}