{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:25:48Z","timestamp":1777656348778,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729690","type":"print"},{"value":"9783031729706","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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\/978-3-031-72970-6_4","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T10:49:19Z","timestamp":1732272559000},"page":"56-72","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Make Your ViT-Based Multi-view 3D Detectors Faster via\u00a0Token Compression"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5022-8172","authenticated-orcid":false,"given":"Dingyuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3035-1373","authenticated-orcid":false,"given":"Dingkang","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8501-4123","authenticated-orcid":false,"given":"Zichang","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3268-880X","authenticated-orcid":false,"given":"Xiaoqing","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6831-5103","authenticated-orcid":false,"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3449-5940","authenticated-orcid":false,"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"4_CR1","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. In: ICLR (2023)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"4_CR3","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Fang, Y., Sun, Q., Wang, X., Huang, T., Wang, X., Cao, Y.: EVA-02: a visual representation for neon genesis. arXiv preprint arXiv:2303.11331 (2023)","DOI":"10.2139\/ssrn.4813567"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"4_CR6","unstructured":"Huang, J., Huang, G.: BEVDet4D: exploit temporal cues in multi-camera 3D object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"4_CR7","unstructured":"Huang, J., Huang, G.: BEVPoolv2: a cutting-edge implementation of BEVDet toward deployment. arXiv preprint arXiv:2211.17111 (2022)"},{"key":"4_CR8","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: PolarFormer: multi-camera 3D object detection with polar transformer. In: AAAI, vol.\u00a037, pp. 1042\u20131050 (2023)","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"4_CR11","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1007\/978-3-031-20083-0_37","volume-title":"ECCV 2022","author":"Z Kong","year":"2022","unstructured":"Kong, Z., et al.: SPViT: enabling faster vision transformers via latency-aware soft token pruning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13671, pp. 620\u2013640. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_37"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: ECCV, pp. 734\u2013750 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., et\u00a0al.: Fast-BEV: a fast and strong bird\u2019s-eye view perception baseline. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3414835"},{"key":"4_CR14","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-031-20077-9_17","volume-title":"ECCV 2022","author":"Y Li","year":"2022","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 280\u2013296. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection. In: AAAI, vol.\u00a037, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., Lan, S., Alvarez, J.M., Wu, Z.: BEVNeXt: reviving dense BEV frameworks for 3D object detection. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01901"},{"key":"4_CR17","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20077-9_1","volume-title":"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":"4_CR18","doi-asserted-by":"crossref","unstructured":"Li, Z., Yu, Z., Wang, W., Anandkumar, A., Lu, T., Alvarez, J.M.: FB-BEV: BEV representation from forward-backward view transformations. In: ICCV, pp. 6919\u20136928 (2023)","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"4_CR19","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: Not all patches are what you need: expediting vision transformers via token reorganizations. In: ICLR (2022)"},{"key":"4_CR20","unstructured":"Lin, X., Lin, T., Pei, Z., Huang, L., Su, Z.: Sparse4D: multi-view 3D object detection with sparse spatial-temporal fusion. arXiv preprint arXiv:2211.10581 (2022)"},{"key":"4_CR21","unstructured":"Lin, X., Lin, T., Pei, Z., Huang, L., Su, Z.: Sparse4D v2: recurrent temporal fusion with sparse model. arXiv preprint arXiv:2305.14018 (2023)"},{"key":"4_CR22","unstructured":"Lin, X., Pei, Z., Lin, T., Huang, L., Su, Z.: Sparse4D v3: advancing end-to-end 3D detection and tracking. arXiv preprint arXiv:2311.11722 (2023)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Liu, H., Teng, Y., Lu, T., Wang, H., Wang, L.: SparseBEV: high-performance sparse 3D object detection from multi-camera videos. In: ICCV, pp. 18580\u201318590 (2023)","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"4_CR24","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/978-3-031-19812-0_31","volume-title":"ECCV 2022","author":"Y Liu","year":"2022","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.) ECCV 2022. LNCS, vol. 13687, pp. 531\u2013548. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_31"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: PETRv2: a unified framework for 3D perception from multi-camera images. In: ICCV, pp. 3262\u20133272 (2023)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Long, S., Zhao, Z., Pi, J., Wang, S., Wang, J.: Beyond attentive tokens: incorporating token importance and diversity for efficient vision transformers. In: CVPR, pp. 10334\u201310343 (2023)","DOI":"10.1109\/CVPR52729.2023.00996"},{"key":"4_CR27","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2018)"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Ma, X., Ouyang, W., Simonelli, A., Ricci, E.: 3D object detection from images for autonomous driving: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3346386"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Meng, L., et al.: AdaViT: adaptive vision transformers for efficient image recognition. In: CVPR, pp. 12309\u201312318 (2022)","DOI":"10.1109\/CVPR52688.2022.01199"},{"issue":"1","key":"4_CR30","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"4_CR31","unstructured":"Park, J., et al.: Time will tell: new outlooks and a baseline for temporal multi-view 3D object detection. In: ICLR (2022)"},{"key":"4_CR32","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":"4_CR33","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. In: NeurIPS, vol. 34, pp. 13937\u201313949 (2021)"},{"key":"4_CR34","unstructured":"Roh, B., Shin, J., Shin, W., Kim, S.: Sparse DETR: efficient end-to-end object detection with learnable sparsity. In: ICLR (2021)"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Shu, C., Deng, J., Yu, F., Liu, Y.: 3DPPE: 3D point positional encoding for transformer-based multi-camera 3D object detection. In: ICCV, pp. 3580\u20133589 (2023)","DOI":"10.1109\/ICCV51070.2023.00331"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Wang, S., Liu, Y., Wang, T., Li, Y., Zhang, X.: Exploring object-centric temporal modeling for efficient multi-view 3D object detection. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"4_CR37","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: Detr3D: 3D object detection from multi-view images via 3D-to-2D queries. In: Conference on Robot Learning, pp. 180\u2013191. PMLR (2022)"},{"key":"4_CR38","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. vol. 34, pp. 12077\u201312090 (2021)"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Xiong, K., et al.: Cape: camera view position embedding for multi-view 3D object detection. In: CVPR, pp. 21570\u201321579 (2023)","DOI":"10.1109\/CVPR52729.2023.02066"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Evo-ViT: slow-fast token evolution for dynamic vision transformer. In: AAAI, vol.\u00a036, pp. 2964\u20132972 (2022)","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"4_CR41","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: CVPR, pp. 17830\u201317839 (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Yin, H., Vahdat, A., Alvarez, J.M., Mallya, A., Kautz, J., Molchanov, P.: A-ViT: adaptive tokens for efficient vision transformer. In: CVPR, pp. 10809\u201310818 (2022)","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, D., et al.: SAM3D: zero-shot 3D object detection via segment anything model. Sci. China Inf. Sci. (2024)","DOI":"10.1007\/s11432-023-3943-6"},{"key":"4_CR44","unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3D object detection. arXiv preprint arXiv:1908.09492 (2019)"}],"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\/978-3-031-72970-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T11:11:37Z","timestamp":1732273897000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72970-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031729690","9783031729706"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72970-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 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"}}]}}