{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T08:04:53Z","timestamp":1773734693820,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"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":[[2025,11,18]]},"DOI":"10.1109\/itsc60802.2025.11423431","type":"proceedings-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:10:23Z","timestamp":1773691823000},"page":"4275-4282","source":"Crossref","is-referenced-by-count":0,"title":["DSATFusion: Multi-Modal 3D Detection via Vision-Text Synergy with Dynamic Sparse Attention Temporal Fusion"],"prefix":"10.1109","author":[{"given":"Yiheng","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Earth Science and Engineering, Hohai University,Nanjing,China,211100"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China,511453"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haipeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China,511453"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Land and Environment, Shenyang Agricultural University,Shenyang,China,110866"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jiangsu Ocean University,Lianyungang,China,222005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junlan","family":"Chen","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China,211189"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shandong","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Geography and Remote Sensing, Hohai University,Nanjing,China,211100"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102793"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00335"},{"key":"ref3","article-title":"Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion","author":"Lin","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref4","article-title":"DETR4D: Direct MultiView 3D Object Detection with Sparse Attention","author":"Luo","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"BEVDet: Highperformance Multi-camera 3D Object Detection in Bird-Eye-View","author":"Huang","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref9","article-title":"Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection","author":"Park","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref10","first-page":"180","article-title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","volume-title":"Conference on Robot Learning","author":"Wang","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref12","article-title":"Sparse4D v2: Recurrent Temporal Fusion with Sparse Model","author":"Lin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref13","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref14","first-page":"19730","article-title":"BLIP-2: Bootstrapping LanguageImage Pre-training with Frozen Image Encoders and Large Language Models","volume-title":"International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01845"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref19","article-title":"BEVDet4D: Exploit Temporal Cues in Multicamera 3D Object Detection","author":"Huang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3401172"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01703"},{"key":"ref22","first-page":"4904","article-title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","volume-title":"International Conference on Machine Learning","author":"Jia","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00120"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref26","first-page":"arXiv2401","article-title":"BEV-CLIP: Multi-modal BEV Retrieval Methodology for Complex Scene in Autonomous Driving","author":"Wei","year":"2024","journal-title":"ArXiv E-prints"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","article-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref30","article-title":"Generating Long Sequences with Sparse Transformers","author":"Child","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1032"},{"key":"ref32","article-title":"Reformer: The Efficient Transformer","author":"Kitaev","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref33","article-title":"Longformer: The LongDocument Transformer","author":"Beltagy","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref37","article-title":"Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection","author":"Zhu","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","location":"Gold Coast, Australia","start":{"date-parts":[[2025,11,18]]},"end":{"date-parts":[[2025,11,21]]}},"container-title":["2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11422813\/11423000\/11423431.pdf?arnumber=11423431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:48:44Z","timestamp":1773726524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11423431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/itsc60802.2025.11423431","relation":{},"subject":[],"published":{"date-parts":[[2025,11,18]]}}}