{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:05:46Z","timestamp":1743026746175,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787012"},{"type":"electronic","value":"9789819787029"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-97-8702-9_10","type":"book-chapter","created":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T14:47:43Z","timestamp":1738939663000},"page":"142-156","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BEVFormer\u2019s Plugin: Integrating Historical Detection Data, BEV-Level Information, Time Information, and\u00a0Depth Information"],"prefix":"10.1007","author":[{"given":"Zeen","family":"Pan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongyang","family":"Tong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhan","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,8]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., et\u00a0al.: 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":"10_CR2","doi-asserted-by":"crossref","unstructured":"Han, T., Xie, W., Zisserman, A.: Memory-augmented dense predictive coding for video representation learning. In: European Conference on Computer Vision, pp. 312\u2013329. Springer International Publishing (2020)","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J., et\u00a0al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR4","unstructured":"Huang, J., Huang, G.: Bevdet4d: exploit temporal cues in multi-camera 3d object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"issue":"10","key":"10_CR5","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.1109\/TCSVT.2017.2736553","volume":"28","author":"K Kang","year":"2017","unstructured":"Kang, K., Li, H., Yan, J., et al.: T-CNN: tubelets with convolutional neural networks for object detection from videos. IEEE Trans. Circuits Syst. Video Technol. 28(10), 2896\u20132907 (2017)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Li, Y., Ge, Z., Yu, G., et\u00a0al.: Bevdepth: acquisition of reliable depth for multi-view 3d object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., et\u00a0al.: Bevformer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: European Conference on Computer Vision, pp. 1\u201318. Springer Nature Switzerland (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., et\u00a0al.: Microsoft coco: common objects in context. In: European Conference on Computer Vision (ECCV), pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10_CR9","unstructured":"Lin, X., Lin, T., Pei, Z., et\u00a0al.: Sparse4d: multi-view 3d object detection with sparse spatial-temporal fusion. arXiv preprint arXiv:2211.10581 (2022)"},{"key":"10_CR10","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"10_CR11","unstructured":"Park, J., Xu, C., Yang, S., et\u00a0al.: Time will tell: new outlooks and a baseline for temporal multi-view 3d object detection. In: The Eleventh International Conference on Learning Representations (September 2022)"},{"key":"10_CR12","unstructured":"Ren, S., He, K., Girshick, R., et\u00a0al.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Shu, C., Deng, J., Yu, F., Liu, Y.: 3DPPE: 3d point positional encoding for multi-camera 3d object detection transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00331"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bulo, S.R., Porzi, L., et\u00a0al.: Disentangling monocular 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1991\u20131999 (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Singh, G., Choutas, V., Saha, S., et\u00a0al.: Spatio-temporal action detection under large motion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6009\u20136018 (2023)","DOI":"10.1109\/WACV56688.2023.00595"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Wang, S., Liu, Y., Wang, T., et\u00a0al.: Exploring object-centric temporal modeling for efficient multi-view 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3621\u20133631 (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"10_CR17","unstructured":"Wang, T., Lian, Q., Zhu, C., et\u00a0al.: MV-FCOS3D++: multi-view camera-only 4d object detection with pretrained monocular backbones. arXiv preprint arXiv:2207.12716 (2022)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Yang, C., Chen, Y., Tian, H., 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":"10_CR19","unstructured":"Zhang, H., Li, H., Zeng, A., et\u00a0al.: Introducing depth into transformer-based 3d object detection. arXiv preprint arXiv:2302.13002 (2023)"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zheng, W., Zhu, Z., et\u00a0al.: A simple baseline for multi-camera 3d object detection. arXiv preprint arXiv:2208.10035 (2022)","DOI":"10.1609\/aaai.v37i3.25460"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., et\u00a0al.: Flow-guided feature aggregation for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 408\u2013417 (2017)","DOI":"10.1109\/ICCV.2017.52"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Zong, Z., Jiang, D., Song, G., et\u00a0al.: Temporal enhanced training of multi-view 3d object detector via historical object prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3781\u20133790 (2023)","DOI":"10.1109\/ICCV51070.2023.00350"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8702-9_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T14:48:03Z","timestamp":1738939683000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8702-9_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819787012","9789819787029"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8702-9_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"8 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPRAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"18 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icprai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/brain.korea.ac.kr\/icprai2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}