{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:15:29Z","timestamp":1756167329053,"version":"3.44.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,24]]},"DOI":"10.1109\/itsc58415.2024.10920182","type":"proceedings-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T15:00:11Z","timestamp":1742569211000},"page":"3989-3996","source":"Crossref","is-referenced-by-count":0,"title":["Learning Content-Aware Multi-Modal Joint Input Pruning via Birds'-Eye-View Representation"],"prefix":"10.1109","author":[{"given":"Yuxin","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xulei","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengying","family":"Yu","sequence":"additional","affiliation":[{"name":"Desay SV Automotive,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihang","family":"Huang","sequence":"additional","affiliation":[{"name":"Desay SV Automotive,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Wu","sequence":"additional","affiliation":[{"name":"Desay SV Automotive,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chai Kiat","family":"Yeo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Bevformer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers","volume-title":"European Conference on Computer Vision (ECCV)","volume":"13669","author":"et al","year":"2022"},{"key":"ref2","article-title":"Beverse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving","volume":"abs\/2205.09743","author":"Zhang","year":"2022","journal-title":"arXiv"},{"key":"ref3","article-title":"M2 bev: Multi-camera joint 3d detection and segmentation with unified birds-eye view representation","volume":"abs\/2204.05088","author":"Xie","year":"2022","journal-title":"arXiv"},{"key":"ref4","article-title":"Bevdet4d: Exploit temporal cues in multicamera 3d object detection","volume":"abs\/2203.17054","author":"Huang","year":"2022","journal-title":"arxiv"},{"key":"ref5","article-title":"Bevdepth: Acquisition of reliable depth for multi-view 3d object detection","volume":"abs\/2206.10092","author":"et al","year":"2022","journal-title":"arxiv"},{"key":"ref6","article-title":"Bevdet: Highperformance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00588"},{"key":"ref13","first-page":"22352","article-title":"Vectormapnet: End-to-end vectorized HD map learning","volume-title":"International Conference on Machine Learning, ICML, ser. Proceedings of Machine Learning Research","volume":"202","author":"Liu","year":"2023"},{"key":"ref14","article-title":"Maptr: Structured modeling and learning for online vectorized HD map construction","volume-title":"International Conference on Learning Representations","author":"Liao","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref16","article-title":"Pruning filters for efficient convnets","volume-title":"International Conference on Learning Representations, ICLR","author":"Li","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01544"},{"key":"ref18","article-title":"Pruning attention heads of transformer models using a* search: A novel approach to compress big NLP architectures","volume":"abs\/2110.15225","author":"Parnami","year":"2021","journal-title":"arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539260"},{"key":"ref21","article-title":"Pruning self-attentions into convolutional layers in single path","volume":"abs\/2111.11802","author":"He","year":"2021","journal-title":"arxiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref23","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning, ICML, ser. Proceedings of Machine Learning Research","volume":"139","author":"Touvron"},{"key":"ref24","article-title":"Lift, splat, shoot:Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d","volume-title":"European Conference on Computer Vision (ECCV)","author":"Philion","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref27","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"The Conference on Robot Learning (CoRL)","author":"Wang","year":"2021"},{"key":"ref28","first-page":"531","article-title":"PETR: position embedding transformation for multi-view 3d object detection","volume-title":"European Conference on Computer Vision (ECCV)","volume":"13687","author":"et al","year":"2022"},{"key":"ref29","article-title":"CAPE: camera view position embedding for multi-view 3d object detection","volume":"abs\/2303.10209","author":"et al","year":"2023","journal-title":"arxiv"},{"key":"ref30","first-page":"16494","article-title":"Multimodal virtual point 3d detection","author":"Yin","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_8"},{"key":"ref36","article-title":"Class-balanced grouping and sampling for point cloud 3d object detection","volume":"abs\/1908.09492","author":"Zhu","year":"2019","journal-title":"arxiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","start":{"date-parts":[[2024,9,24]]},"location":"Edmonton, AB, Canada","end":{"date-parts":[[2024,9,27]]}},"container-title":["2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10919469\/10919190\/10920182.pdf?arnumber=10920182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:13:19Z","timestamp":1756152799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10920182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,24]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/itsc58415.2024.10920182","relation":{},"subject":[],"published":{"date-parts":[[2024,9,24]]}}}