{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:48:17Z","timestamp":1775076497816,"version":"3.50.1"},"reference-count":47,"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\/itsc58415.2024.10920115","type":"proceedings-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T19:00:11Z","timestamp":1742583611000},"page":"2027-2034","source":"Crossref","is-referenced-by-count":7,"title":["MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detection"],"prefix":"10.1109","author":[{"given":"Xiangbo","family":"Gao","sequence":"first","affiliation":[{"name":"University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109"}]},{"given":"Asiegbu Miracle","family":"Kanu-Asiegbu","sequence":"additional","affiliation":[{"name":"University of Michigan,Department of Mechanical Engineering,Ann Arbor,MI,USA,48109"}]},{"given":"Xiaoxiao","family":"Du","sequence":"additional","affiliation":[{"name":"University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564853"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10421911"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3162719"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.73"},{"key":"ref5","article-title":"Multispectral pedestrian detection via simultaneous detection and segmentation","author":"Li","year":"2018","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00012"},{"issue":"6","key":"ref8","article-title":"Multimodal object detection via bayesian fusion","volume":"3","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref12","first-page":"6202","article-title":"Slow-fast networks for video recognition","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Feichtenhofer","year":"2019"},{"key":"ref13","article-title":"Tada! temporally-adaptive convolutions for video understanding","volume-title":"International Conference on Learning Representations","author":"Huang","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref16","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/app14135683"},{"key":"ref20","article-title":"A survey on vision mamba: Models, applications and challenges","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref22","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298706"},{"key":"ref24","article-title":"Fusion-mamba for cross-modality object detection","author":"Dong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Cfmw: Cross-modality fusion mamba for multispectral object detection under adverse weather conditions","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Fusionmamba: Efficient image fusion with state space model","author":"Peng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3146575"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306870"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2015.7225711"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917447"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294537"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCS50536.2020.9310031"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00049"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00523"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3022623"},{"key":"ref37","first-page":"139","article-title":"Multimodal object detection via probabilis-tic ensembling","volume-title":"European Conference on Computer Vision","author":"Chen","year":"2022"},{"key":"ref38","article-title":"Cross-modality fusion transformer for multispectral object detection","author":"Qingyun","year":"2021","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_41"},{"key":"ref40","article-title":"Ms-detr: Multispectral pedestrian detection transformer with loosely coupled fusion and modality-balanced optimization","author":"Xing","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3266487"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/s24041168"},{"key":"ref43","article-title":"Pyramid attention network for semantic segmentation","author":"Li","year":"2018","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290594"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191080"}],"event":{"name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","location":"Edmonton, AB, Canada","start":{"date-parts":[[2024,9,24]]},"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\/10920115.pdf?arnumber=10920115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T21:06:58Z","timestamp":1742591218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10920115\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,24]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/itsc58415.2024.10920115","relation":{},"subject":[],"published":{"date-parts":[[2024,9,24]]}}}