{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:26:41Z","timestamp":1743046001347,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819601219"},{"type":"electronic","value":"9789819601226"}],"license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"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\/978-981-96-0122-6_21","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T18:24:46Z","timestamp":1731781486000},"page":"233-245","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BEVTemp: Enhancing Vision-Based Roadside 3D Object Detection with\u00a0Temporal Information"],"prefix":"10.1007","author":[{"given":"Gaoyuan","family":"Miao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rong","family":"Quan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiheng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Brazil, G., Liu, X.: M3d-rpn: monocular 3d region proposal network for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9287\u20139296 (2019)","DOI":"10.1109\/ICCV.2019.00938"},{"key":"21_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-030-58592-1_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Brazil","year":"2020","unstructured":"Brazil, G., Pons-Moll, G., Liu, X., Schiele, B.: Kinematic 3D object detection in\u00a0monocular video. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 135\u2013152. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_9"},{"key":"21_CR3","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":"21_CR4","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"21_CR5","unstructured":"Huang, J., Huang, G.: Bevdet4d: exploit temporal cues in multi-camera 3d object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Li, Y., Bao, H., Ge, Z., Yang, J., Sun, J., Li, Z.: Bevstereo: enhancing depth estimation in multi-view 3d object detection with temporal stereo. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1486\u20131494 (2023)","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"21_CR8","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, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"21_CR9","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from\u00a0multi-camera images via\u00a0spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part IX, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"21_CR11","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Ma, X., et al.: Delving into localization errors for monocular 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4721\u20134730 (2021)","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"21_CR13","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"},{"issue":"3","key":"21_CR14","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1109\/JAS.2023.123660","volume":"11","author":"C Pan","year":"2024","unstructured":"Pan, C., Peng, J., Zhang, Z.: Depth-guided vision transformer with normalizing flows for monocular 3d object detection. IEEE\/CAA J. Automat. Sinica 11(3), 673\u2013689 (2024)","journal-title":"IEEE\/CAA J. Automat. Sinica"},{"key":"21_CR15","unstructured":"Park, J., et al.: Time will tell: new outlooks and a baseline for temporal multi-view 3d object detection. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Rukhovich, D., Vorontsova, A., Konushin, A.: Imvoxelnet: image to voxels projection for monocular and multi-view general-purpose 3d object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2397\u20132406 (2022)","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bulo, S.R., Porzi, L., L\u00f3pez-Antequera, M., Kontschieder, P.: Disentangling monocular 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1991\u20131999 (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Zhou, Y., Tuzel, O.: Mvx-net: multimodal voxelnet for 3d object detection. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 7276\u20137282. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, F., Bi, H.: Gaussian focal loss: learning distribution polarized angle prediction for rotated object detection in aerial images. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2022)","DOI":"10.1109\/TGRS.2022.3175520"},{"issue":"10","key":"21_CR20","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","journal-title":"Sensors"},{"key":"21_CR21","unstructured":"Yang, L., et al.: Bevheight++: toward robust visual centric 3d object detection. arXiv preprint arXiv:2309.16179 (2023)"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Bevheight: a robust framework for vision-based roadside 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21611\u201321620 (2023)","DOI":"10.1109\/CVPR52729.2023.02070"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Ye, X., et al.: Rope3d: the roadside perception dataset for autonomous driving and monocular 3d object detection task. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21341\u201321350 (2022)","DOI":"10.1109\/CVPR52688.2022.02065"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Yu, H., et\u00a0al.: Dair-v2x: a large-scale dataset for vehicle-infrastructure cooperative 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21361\u201321370 (2022)","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, J., Zhou, J.: Objects are different: flexible monocular 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3289\u20133298 (2021)","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: more deformable, better results. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9308\u20139316 (2019)","DOI":"10.1109\/CVPR.2019.00953"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2024: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0122-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T19:19:44Z","timestamp":1731784784000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0122-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"ISBN":["9789819601219","9789819601226"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0122-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"12 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}