{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T22:53:02Z","timestamp":1769640782901,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"funder":[{"name":"Science and Technology Development Fund, Macau SAR","award":["Grant 0075\/2023\/AMJ, Grant 0003\/2023\/RIB1, and Grant 001\/2024\/SKL"],"award-info":[{"award-number":["Grant 0075\/2023\/AMJ, Grant 0003\/2023\/RIB1, and Grant 001\/2024\/SKL"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100007162","name":"Guangdong Science and Technology Department","doi-asserted-by":"publisher","award":["Grant 2023A0505030003, Grant 2020B1515130001"],"award-info":[{"award-number":["Grant 2023A0505030003, Grant 2020B1515130001"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100007162","id-type":"DOI","asserted-by":"publisher"}]},{"name":"International Science and Technology Project of Guangzhou Development District","award":["Grant 2022GH09"],"award-info":[{"award-number":["Grant 2022GH09"]}]},{"name":"Zhuhai Science and Technology Innovation Bureau","award":["Grant ZH2220004002524"],"award-info":[{"award-number":["Grant ZH2220004002524"]}]},{"name":"Zhuhai UM Research Institute","award":["Grant HF-011-2021"],"award-info":[{"award-number":["Grant HF-011-2021"]}]},{"name":"University of Macau","award":["Grant MYRG2022-00059-FST, Grant MYRG-GRG2023-00237- FST-UMDF"],"award-info":[{"award-number":["Grant MYRG2022-00059-FST, Grant MYRG-GRG2023-00237- FST-UMDF"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681565","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"9224-9233","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["SparseInteraction: Sparse Semantic Guidance for Radar and Camera 3D Object Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0274-6677","authenticated-orcid":false,"given":"Shaoqing","family":"Xu","sequence":"first","affiliation":[{"name":"University of Macau, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1173-3052","authenticated-orcid":false,"given":"Shengyin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3677-2577","authenticated-orcid":false,"given":"Fang","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5235-5834","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5539-2599","authenticated-orcid":false,"given":"Ziying","family":"Song","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3045-3442","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9151-7758","authenticated-orcid":false,"given":"Zhi-xin","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Macau, Macau, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"e_1_3_2_1_3_1","volume-title":"REDFormer: Radar Enlightens the Darkness of Camera Perception with Transformers","author":"Cui Can","year":"2023","unstructured":"Can Cui, Yunsheng Ma, Juanwu Lu, and Ziran Wang. 2023. REDFormer: Radar Enlightens the Darkness of Camera Perception with Transformers. IEEE Transactions on Intelligent Vehicles (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_6_1","unstructured":"Chunyong Hu Hang Zheng Kun Li Jianyun Xu Weibo Mao Maochun Luo Lingxuan Wang Mingxia Chen Kaixuan Liu Yiru Zhao et al. 2023. FusionFormer: a multi-sensory fusion in bird's-eye-view and temporal consistent transformer for 3D objection. arXiv preprint arXiv:2309.05257 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790","author":"Huang Junjie","year":"2021","unstructured":"Junjie Huang, Guan Huang, Zheng Zhu, Yun Ye, and Dalong Du. 2021. Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_23"},{"key":"e_1_3_2_1_9_1","volume-title":"RCM-Fusion: Radar-Camera Multi-Level Fusion for 3D Object Detection. arXiv preprint arXiv:2307.10249","author":"Kim Jisong","year":"2023","unstructured":"Jisong Kim, Minjae Seong, Geonho Bang, Dongsuk Kum, and Jun Won Choi. 2023. RCM-Fusion: Radar-Camera Multi-Level Fusion for 3D Object Detection. arXiv preprint arXiv:2307.10249 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25198"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01615"},{"key":"e_1_3_2_1_12_1","volume-title":"Hvdetfusion: A simple and robust camera-radar fusion framework. arXiv preprint arXiv:2307.11323","author":"Lei Kai","year":"2023","unstructured":"Kai Lei, Zhan Chen, Shuman Jia, and Xiaoteng Zhang. 2023. Hvdetfusion: A simple and robust camera-radar fusion framework. arXiv preprint arXiv:2307.11323 (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01589"},{"key":"e_1_3_2_1_21_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00157"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings, Part XIV 16","author":"Philion Jonah","year":"2020","unstructured":"Jonah Philion and Sanja Fidler. 2020. Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XIV 16. Springer, 194--210."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_3"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306361"},{"key":"e_1_3_2_1_27_1","volume-title":"Robustness-Aware 3D Object Detection in Autonomous Driving: A Review and Outlook. arXiv preprint arXiv:2401.06542","author":"Song Ziying","year":"2024","unstructured":"Ziying Song, Lin Liu, Feiyang Jia, Yadan Luo, Guoxin Zhang, Lei Yang, Li Wang, and Caiyan Jia. 2024. Robustness-Aware 3D Object Detection in Autonomous Driving: A Review and Outlook. arXiv preprint arXiv:2401.06542 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Robofusion: Towards robust multi-modal 3d obiect detection via sam. arXiv preprint arXiv:2401.03907","author":"Song Ziying","year":"2024","unstructured":"Ziying Song, Guoxing Zhang, Lin Liu, Lei Yang, Shaoqing Xu, Caiyan Jia, Feiyang Jia, and Li Wang. 2024. Robofusion: Towards robust multi-modal 3d obiect detection via sam. arXiv preprint arXiv:2401.03907 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Voxelnextfusion: A simple, unified and effective voxel fusion framework for multi-modal 3d object detection. arXiv preprint arXiv:2401.02702","author":"Song Ziying","year":"2024","unstructured":"Ziying Song, Guoxin Zhang, Jun Xie, Lin Liu, Caiyan Jia, Shaoqing Xu, and Zhepeng Wang. 2024. Voxelnextfusion: A simple, unified and effective voxel fusion framework for multi-modal 3d object detection. arXiv preprint arXiv:2401.02702 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3025798"},{"key":"e_1_3_2_1_31_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108892"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3186035"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"e_1_3_2_1_35_1","volume-title":"Conference on Robot Learning. PMLR, 180--191","author":"Wang Yue","year":"2022","unstructured":"Yue Wang, Vitor Campagnolo Guizilini, Tianyuan Zhang, Yilun Wang, Hang Zhao, and Justin Solomon. 2022. Detr3d: 3d object detection from multi-view images via 3d-to-2d queries. In Conference on Robot Learning. PMLR, 180--191."},{"key":"e_1_3_2_1_36_1","volume-title":"Mvfusion: Multi-view 3d object detection with semantic-aligned radar and camera fusion. arXiv preprint arXiv:2302.10511","author":"Wu Zizhang","year":"2023","unstructured":"Zizhang Wu, Guilian Chen, Yuanzhu Gan, Lei Wang, and Jian Pu. 2023. Mvfusion: Multi-view 3d object detection with semantic-aligned radar and camera fusion. arXiv preprint arXiv:2302.10511 (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection. arXiv preprint arXiv:2304.14340","author":"Xie Yichen","year":"2023","unstructured":"Yichen Xie, Chenfeng Xu, Marie-Julie Rakotosaona, Patrick Rim, Federico Tombari, Kurt Keutzer, Masayoshi Tomizuka, and Wei Zhan. 2023. SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection. arXiv preprint arXiv:2304.14340 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Multi-Sem Fusion: Multimodal Semantic Fusion for 3D Object Detection","author":"Xu Shaoqing","year":"2024","unstructured":"Shaoqing Xu, Fang Li, Ziying Song, Jin Fang, Sifen Wang, and Zhi-Xin Yang. 2024. Multi-Sem Fusion: Multimodal Semantic Fusion for 3D Object Detection. IEEE Transactions on Geoscience and Remote Sensing (2024), 1--1."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"e_1_3_2_1_40_1","volume-title":"Efficient detr: improving end-to-end object detector with dense prior. arXiv preprint arXiv:2104.01318","author":"Yao Zhuyu","year":"2021","unstructured":"Zhuyu Yao, Jiangbo Ai, Boxun Li, and Chi Zhang. 2021. Efficient detr: improving end-to-end object detector with dense prior. arXiv preprint arXiv:2104.01318 (2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"Dual radar: A multi-modal dataset with dual 4d radar for autononous driving. arXiv preprint arXiv:2310.07602","author":"Zhang Xinyu","year":"2023","unstructured":"Xinyu Zhang, Li Wang, Jian Chen, Cheng Fang, Lei Yang, Ziying Song, Guangqi Yang, Yichen Wang, Xiaofei Zhang, and Jun Li. 2023. Dual radar: A multi-modal dataset with dual 4d radar for autononous driving. arXiv preprint arXiv:2310.07602 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3240287"},{"key":"e_1_3_2_1_43_1","volume-title":"Class-balanced grouping and sampling for point cloud 3d object detection. arXiv preprint arXiv:1908.09492","author":"Zhu Benjin","year":"2019","unstructured":"Benjin Zhu, Zhengkai Jiang, Xiangxin Zhou, Zeming Li, and Gang Yu. 2019. Class-balanced grouping and sampling for point cloud 3d object detection. arXiv preprint arXiv:1908.09492 (2019)."},{"key":"e_1_3_2_1_44_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681565","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:48Z","timestamp":1750295868000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681565"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":44,"alternative-id":["10.1145\/3664647.3681565","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681565","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}