{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:19:18Z","timestamp":1765340358587,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754550","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"2526-2535","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Contextually-Guided State Space Fusion for Misaligned Multi-Spectral Object Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0658-9017","authenticated-orcid":false,"given":"Guyue","family":"Jin","sequence":"first","affiliation":[{"name":"National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1782-4781","authenticated-orcid":false,"given":"Tianming","family":"Zhao","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5608-9838","authenticated-orcid":false,"given":"Jiacan","family":"Yan","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0148-4900","authenticated-orcid":false,"given":"Tian","family":"Tian","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3146575"},{"key":"e_1_3_2_1_2_1","volume-title":"Fusion-mamba for cross-modality object detection. arXiv preprint arXiv:2404.09146","author":"Dong Wenhao","year":"2024","unstructured":"Wenhao Dong, Haodong Zhu, Shaohui Lin, Xiaoyan Luo, Yunhang Shen, Xuhui Liu, Juan Zhang, Guodong Guo, and Baochang Zhang. 2024. Fusion-mamba for cross-modality object detection. arXiv preprint arXiv:2404.09146 (2024)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/s16060820"},{"key":"e_1_3_2_1_4_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396","author":"Gu Albert","year":"2021","unstructured":"Albert Gu, Karan Goel, and Christopher R\u00e9. 2021. Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.11.017"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612651"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3375634"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.36"},{"key":"e_1_3_2_1_12_1","volume-title":"Multispectral pedestrian detection via simultaneous detection and segmentation. arXiv preprint arXiv:1808.04818","author":"Li Chengyang","year":"2018","unstructured":"Chengyang Li, Dan Song, Ruofeng Tong, and Min Tang. 2018. Multispectral pedestrian detection via simultaneous detection and segmentation. arXiv preprint arXiv:1808.04818 (2018)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.08.005"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"e_1_3_2_1_17_1","volume-title":"Multispectral deep neural networks for pedestrian detection. arXiv preprint arXiv:1611.02644","author":"Liu Jingjing","year":"2016","unstructured":"Jingjing Liu, Shaoting Zhang, Shu Wang, and Dimitris N Metaxas. 2016. Multispectral deep neural networks for pedestrian detection. arXiv preprint arXiv:1611.02644 (2016)."},{"key":"e_1_3_2_1_18_1","first-page":"103031","article-title":"Vmamba: Visual state space model","volume":"37","author":"Liu Yue","year":"2024","unstructured":"Yue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu, Lingxi Xie, Yaowei Wang, Qixiang Ye, Jianbin Jiao, and Yunfan Liu. 2024. Vmamba: Visual state space model. Advances in Neural Information Processing Systems, Vol. 37 (2024), 103031-103063.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Data Science and Network Engineering. Springer, 125-141","author":"Mehla Nandni","year":"2023","unstructured":"Nandni Mehla, Ishita, Ritika Talukdar, and Deepak Kumar Sharma. 2023. Object detection in autonomous maritime vehicles: comparison between YOLO V8 and EfficientDet. In International Conference on Data Science and Network Engineering. Springer, 125-141."},{"key":"e_1_3_2_1_20_1","volume-title":"Cross-modality fusion transformer for multispectral object detection. arXiv preprint arXiv:2111.00273","author":"Qingyun Fang","year":"2021","unstructured":"Fang Qingyun, Han Dapeng, and Wang Zhaokui. 2021. Cross-modality fusion transformer for multispectral object detection. arXiv preprint arXiv:2111.00273 (2021)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109913"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3168279"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-022-01771-9"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3452550"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs15030660"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00072-9"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08239-z"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_30"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00012"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00523"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3273818"},{"key":"e_1_3_2_1_35_1","volume-title":"TFDet: Target-aware fusion for RGB-T pedestrian detection","author":"Zhang Xue","year":"2024","unstructured":"Xue Zhang, Xiaohan Zhang, Jiangtao Wang, Jiacheng Ying, Zehua Sheng, Heng Yu, Chunguang Li, and Hui-Liang Shen. 2024. TFDet: Target-aware fusion for RGB-T pedestrian detection. IEEE Transactions on Neural Networks and Learning Systems (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3022623"},{"key":"e_1_3_2_1_37_1","first-page":"1","article-title":"Illumination-guided RGBT object detection with inter-and intra-modality fusion","volume":"72","author":"Zhang Yan","year":"2023","unstructured":"Yan Zhang, Huai Yu, Yujie He, Xinya Wang, and Wen Yang. 2023b. Illumination-guided RGBT object detection with inter-and intra-modality fusion. IEEE Transactions on Instrumentation and Measurement, Vol. 72 (2023), 1-13.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_46"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3266487"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:14:34Z","timestamp":1765340074000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754550"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":39,"alternative-id":["10.1145\/3746027.3754550","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754550","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}