{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:22:40Z","timestamp":1777569760508,"version":"3.51.4"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730207","type":"print"},{"value":"9783031730214","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73021-4_2","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:14:37Z","timestamp":1732094077000},"page":"19-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["FipTR: A Simple yet\u00a0Effective Transformer Framework for\u00a0Future Instance Prediction in\u00a0Autonomous Driving"],"prefix":"10.1007","author":[{"given":"Xingtai","family":"Gui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tengteng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haonan","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haotian","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"2_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1007\/978-3-031-19839-7_26","volume-title":"Computer Vision \u2013 ECCV 2022","author":"AK Akan","year":"2022","unstructured":"Akan, A.K., G\u00fcney, F.: StretchBEV: stretching future instance prediction spatially and temporally. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13698, pp. 444\u2013460. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_26"},{"key":"2_CR2","unstructured":"Bartoccioni, F., Zablocki, \u00c9., Bursuc, A., P\u00e9rez, P., Cord, M., Alahari, K.: LaRa: latents and rays for multi-camera bird\u2019s-eye-view semantic segmentation. In: Conference on Robot Learning, pp. 1663\u20131672. PMLR (2023)"},{"key":"2_CR3","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":"2_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"2_CR5","unstructured":"Casas, S., Luo, W., Urtasun, R.: IntentNet: learning to predict intention from raw sensor data. In: Conference on Robot Learning, pp. 947\u2013956. PMLR (2018)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"2_CR7","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 17864\u201317875 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Fang, S., Wang, Z., Zhong, Y., Ge, J., Chen, S.: TBP-former: learning temporal bird\u2019s-eye-view pyramid for joint perception and prediction in vision-centric autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1368\u20131378 (2023)","DOI":"10.1109\/CVPR52729.2023.00138"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Gu, J., Sun, C., Zhao, H.: DenseTNT: end-to-end trajectory prediction from dense goal sets. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15303\u201315312 (2021)","DOI":"10.1109\/ICCV48922.2021.01502"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Heo, M., et al.: A generalized framework for video instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14623\u201314632 (2023)","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Hu, A., et al.: FIERY: future instance prediction in bird\u2019s-eye view from surround monocular cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15273\u201315282 (2021)","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Hu, Y., et\u00a0al.: Planning-oriented autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17853\u201317862 (2023)","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"2_CR14","unstructured":"Huang, J., Huang, G.: BEVDet4D: exploit temporal cues in multi-camera 3D object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"2_CR15","unstructured":"Huang, J., Huang, G., Zhu, Z., Du, D.: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Jain, J., Li, J., Chiu, M.T., Hassani, A., Orlov, N., Shi, H.: OneFormer: one transformer to rule universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2989\u20132998 (2023)","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Kim, D., Woo, S., Lee, J.Y., Kweon, I.S.: Video panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9859\u20139868 (2020)","DOI":"10.1109\/CVPR42600.2020.00988"},{"issue":"1\u20132","key":"2_CR18","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logis. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logis. Q."},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Li, P., Ding, S., Chen, X., Hanselmann, N., Cordts, M., Gall, J.: PowerBEV: a powerful yet lightweight framework for instance prediction in bird\u2019s-eye view. arXiv preprint arXiv:2306.10761 (2023)","DOI":"10.24963\/ijcai.2023\/120"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"2_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20077-9_1","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Z Li","year":"2022","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Liang, M., et al.: PnPNet: end-to-end perception and prediction with tracking in the loop. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11553\u201311562 (2020)","DOI":"10.1109\/CVPR42600.2020.01157"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"2_CR24","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"},{"issue":"2","key":"2_CR25","doi-asserted-by":"publisher","first-page":"5639","DOI":"10.1109\/LRA.2022.3151613","volume":"7","author":"R Mahjourian","year":"2022","unstructured":"Mahjourian, R., Kim, J., Chai, Y., Tan, M., Sapp, B., Anguelov, D.: Occupancy flow fields for motion forecasting in autonomous driving. IEEE Robot. Autom. Lett. 7(2), 5639\u20135646 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: TrackFormer: multi-object tracking with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8844\u20138854 (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Pan, C., He, Y., Peng, J., Zhang, Q., Sui, W., Zhang, Z.: BAEFormer: bi-directional and early interaction transformers for bird\u2019s eye view semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9590\u20139599 (2023)","DOI":"10.1109\/CVPR52729.2023.00925"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Peng, L., Chen, Z., Fu, Z., Liang, P., Cheng, E.: BEVSegFormer: bird\u2019s eye view semantic segmentation from arbitrary camera rigs. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5935\u20135943 (2023)","DOI":"10.1109\/WACV56688.2023.00588"},{"key":"2_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-58568-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Philion","year":"2020","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Qin, Z., Chen, J., Chen, C., Chen, X., Li, X.: UniFusion: unified multi-view fusion transformer for spatial-temporal representation in bird\u2019s-eye-view. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8690\u20138699 (2023)","DOI":"10.1109\/ICCV51070.2023.00798"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Tong, W., et\u00a0al.: Scene as occupancy. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8406\u20138415 (2023)","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: End-to-end video instance segmentation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8741\u20138750 (2021)","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"2_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1007\/978-3-031-19815-1_32","volume-title":"Computer Vision \u2013 ECCV 2022","author":"J Wu","year":"2022","unstructured":"Wu, J., Jiang, Y., Bai, S., Zhang, W., Bai, X.: SeqFormer: sequential transformer for video instance segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 553\u2013569. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_32"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Yang, C., et\u00a0al.: BEVFormer v2: adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17830\u201317839 (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"2_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/978-3-031-19812-0_38","volume-title":"Computer Vision \u2013 ECCV 2022","author":"F Zeng","year":"2022","unstructured":"Zeng, F., Dong, B., Zhang, Y., Wang, T., Zhang, X., Wei, Y.: MOTR: end-to-end multiple-object tracking with transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 659\u2013675. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_38"},{"key":"2_CR37","first-page":"10326","volume":"34","author":"W Zhang","year":"2021","unstructured":"Zhang, W., Pang, J., Chen, K., Loy, C.C.: K-net: towards unified image segmentation. Adv. Neural. Inf. Process. Syst. 34, 10326\u201310338 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR38","unstructured":"Zhang, Y., et al.: BEVerse: unified perception and prediction in birds-eye-view for vision-centric autonomous driving. arXiv preprint arXiv:2205.09743 (2022)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, B., Kr\u00e4henb\u00fchl, P.: Cross-view transformers for real-time map-view semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13760\u201313769 (2022)","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"2_CR40","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73021-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:41:14Z","timestamp":1732095674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73021-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031730207","9783031730214"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73021-4_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}