{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:48:09Z","timestamp":1774000089433,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,12]]},"DOI":"10.1145\/3788149.3788248","type":"proceedings-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:35:19Z","timestamp":1773988519000},"page":"361-366","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Lightweight Multi-Modal Framework for 3D Object Detection and Localization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1672-6014","authenticated-orcid":false,"given":"Yuran","family":"Zhang","sequence":"first","affiliation":[{"name":"State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3054-6691","authenticated-orcid":false,"given":"Wenguang","family":"Li","sequence":"additional","affiliation":[{"name":"State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2678-6091","authenticated-orcid":false,"given":"Lingling","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0281-1589","authenticated-orcid":false,"given":"Bin","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Grid Commercial Big Data Co., Ltd., Dongcheng, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Yitao Chen Krishna Gundu Zohair Zaidi and Ming Zhao. 2023. LiDAR-based Outdoor Crowd Management for Smart Campus on the Edge. arxiv:https:\/\/arXiv.org\/abs\/2311.18077\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2311.18077"},{"key":"e_1_3_3_1_3_2","unstructured":"Yukang Chen Yanwei Li Xiangyu Zhang Jian Sun and Jiaya Jia. 2022. Focal Sparse Convolutional Networks for 3D Object Detection. arxiv:https:\/\/arXiv.org\/abs\/2204.12463\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2204.12463"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354978"},{"key":"e_1_3_3_1_5_2","unstructured":"Alex\u00a0H. Lang Sourabh Vora Holger Caesar Lubing Zhou Jiong Yang and Oscar Beijbom. 2019. PointPillars: Fast Encoders for Object Detection from Point Clouds. arxiv:https:\/\/arXiv.org\/abs\/1812.05784\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1812.05784"},{"key":"e_1_3_3_1_6_2","unstructured":"Xingchen Li Yifan Duan Beibei Wang Haojie Ren Guoliang You Yu Sheng Jianmin Ji and Yanyong Zhang. 2023. EdgeCalib: Multi-Frame Weighted Edge Features for Automatic Targetless LiDAR-Camera Calibration. arxiv:https:\/\/arXiv.org\/abs\/2310.16629\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2310.16629"},{"key":"e_1_3_3_1_7_2","unstructured":"Xiaoyan Li Gang Zhang Boyue Wang Yongli Hu and Baocai Yin. 2023. Center Focusing Network for Real-Time LiDAR Panoptic Segmentation. arxiv:https:\/\/arXiv.org\/abs\/2311.09499\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2311.09499"},{"key":"e_1_3_3_1_8_2","unstructured":"Yingwei Li Adams\u00a0Wei Yu Tianjian Meng Ben Caine Jiquan Ngiam Daiyi Peng Junyang Shen Bo Wu Yifeng Lu Denny Zhou Quoc\u00a0V. Le Alan Yuille and Mingxing Tan. 2022. DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection. arxiv:https:\/\/arXiv.org\/abs\/2203.08195\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2203.08195"},{"key":"e_1_3_3_1_9_2","unstructured":"Tsung-Yi Lin Michael Maire Serge Belongie Lubomir Bourdev Ross Girshick James Hays Pietro Perona Deva Ramanan C.\u00a0Lawrence Zitnick and Piotr Doll\u00e1r. 2015. Microsoft COCO: Common Objects in Context. arxiv:https:\/\/arXiv.org\/abs\/1405.0312\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1405.0312"},{"key":"e_1_3_3_1_10_2","unstructured":"Zhijian Liu Haotian Tang Alexander Amini Xinyu Yang Huizi Mao Daniela Rus and Song Han. 2024. BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird\u2019s-Eye View Representation. arxiv:https:\/\/arXiv.org\/abs\/2205.13542\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2205.13542"},{"key":"e_1_3_3_1_11_2","unstructured":"Jiageng Mao Shaoshuai Shi Xiaogang Wang and Hongsheng Li. 2023. 3D Object Detection for Autonomous Driving: A Comprehensive Survey. arxiv:https:\/\/arXiv.org\/abs\/2206.09474\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2206.09474"},{"key":"e_1_3_3_1_12_2","unstructured":"Shaoshuai Shi Chaoxu Guo Li Jiang Zhe Wang Jianping Shi Xiaogang Wang and Hongsheng Li. 2021. PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection. arxiv:https:\/\/arXiv.org\/abs\/1912.13192\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1912.13192"},{"key":"e_1_3_3_1_13_2","unstructured":"Shaoshuai Shi Li Jiang Jiajun Deng Zhe Wang Chaoxu Guo Jianping Shi Xiaogang Wang and Hongsheng Li. 2022. PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection. arxiv:https:\/\/arXiv.org\/abs\/2102.00463\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2102.00463"},{"key":"e_1_3_3_1_14_2","unstructured":"Shaoshuai Shi Xiaogang Wang and Hongsheng Li. 2019. PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud. arxiv:https:\/\/arXiv.org\/abs\/1812.04244\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1812.04244"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Yang Song and Lin Wang. 2025. BiCo-Fusion: Bidirectional Complementary LiDAR-Camera Fusion for Semantic- and Spatial-Aware 3D Object Detection. IEEE Robotics and Automation Letters 10 2 (Feb. 2025) 1457\u20131464. 10.1109\/lra.2024.3518845","DOI":"10.1109\/lra.2024.3518845"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Sourabh Vora Alex\u00a0H. Lang Bassam Helou and Oscar Beijbom. 2020. PointPainting: Sequential Fusion for 3D Object Detection. arxiv:https:\/\/arXiv.org\/abs\/1911.10150\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1911.10150","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"e_1_3_3_1_17_2","unstructured":"Sanghyun Woo Jongchan Park Joon-Young Lee and In\u00a0So Kweon. 2018. CBAM: Convolutional Block Attention Module. arxiv:https:\/\/arXiv.org\/abs\/1807.06521\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1807.06521"},{"key":"e_1_3_3_1_18_2","unstructured":"Jianyun Xu Song Wang Ziqian Ni Chunyong Hu Sheng Yang Jianke Zhu and Qiang Li. 2025. SAM4D: Segment Anything in Camera and LiDAR Streams. arxiv:https:\/\/arXiv.org\/abs\/2506.21547\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2506.21547"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Yan Yan Yuxing Mao and Bo Li. 2018. SECOND: Sparsely Embedded Convolutional Detection. Sensors 18 10 (2018) 3337.","DOI":"10.3390\/s18103337"},{"key":"e_1_3_3_1_20_2","unstructured":"Zeyu Yang Jiaqi Chen Zhenwei Miao Wei Li Xiatian Zhu and Li Zhang. 2022. DeepInteraction: 3D Object Detection via Modality Interaction. arxiv:https:\/\/arXiv.org\/abs\/2208.11112\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2208.11112"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Zetong Yang Yanan Sun Shu Liu and Jiaya Jia. 2020. 3DSSD: Point-based 3D Single Stage Object Detector. arxiv:https:\/\/arXiv.org\/abs\/2002.10187\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2002.10187","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"e_1_3_3_1_22_2","unstructured":"Muhammad Yaseen. 2024. What is YOLOv8: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector. arxiv:https:\/\/arXiv.org\/abs\/2408.15857\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2408.15857"},{"key":"e_1_3_3_1_23_2","unstructured":"Yin Zhou and Oncel Tuzel. 2017. VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection. arxiv:https:\/\/arXiv.org\/abs\/1711.06396\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1711.06396"}],"event":{"name":"CSAI 2025: 2025 The 9th International Conference on Computer Science and Artificial Intelligence","location":"Beijing China","acronym":"CSAI 2025"},"container-title":["Proceedings of the 2025 9th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788149.3788248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:37:33Z","timestamp":1773988653000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788149.3788248"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":22,"alternative-id":["10.1145\/3788149.3788248","10.1145\/3788149"],"URL":"https:\/\/doi.org\/10.1145\/3788149.3788248","relation":{},"subject":[],"published":{"date-parts":[[2025,12,12]]},"assertion":[{"value":"2026-03-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}