{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:30:21Z","timestamp":1760488221872,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,28]]},"DOI":"10.1145\/3732437.3732763","type":"proceedings-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T10:33:54Z","timestamp":1760438034000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LiDAR-Camera Fusion for Video Panoptic Segmentation without Video Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8753-2581","authenticated-orcid":false,"given":"Fardin","family":"Ayar","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Amirkabir University of Technology, Tehran, Iran"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0337-115X","authenticated-orcid":false,"given":"Ehsan","family":"Javanmardi","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Bunky\u014d, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8045-3939","authenticated-orcid":false,"given":"Manabu","family":"Tsukada","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo, Bunky\u014d, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6785-0139","authenticated-orcid":false,"given":"Mahdi","family":"Javanmardi","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Amirkabir University of Technology, Tehran, Iran"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0591-6910","authenticated-orcid":false,"given":"Mohammad","family":"Rahmati","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Amirkabir University of Technology, Tehran, Iran"}]}],"member":"320","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Shariq\u00a0Farooq Bhat Reiner Birkl Diana Wofk Peter Wonka and Matthias M\u00fcller. 2023. Zoedepth: Zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.12288 (2023)."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Luca Caltagirone Mauro Bellone Lennart Svensson and Mattias Wahde. 2019. LIDAR\u2013camera fusion for road detection using fully convolutional neural networks. Robotics and Autonomous Systems 111 (2019) 125\u2013131.","DOI":"10.1016\/j.robot.2018.11.002"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_3_2_5_2","first-page":"12475","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Cheng Bowen","year":"2020","unstructured":"Bowen Cheng, Maxwell\u00a0D Collins, Yukun Zhu, Ting Liu, Thomas\u00a0S Huang, Hartwig Adam, and Liang-Chieh Chen. 2020. Panoptic-deeplab: A simple, strong, and fast baseline for bottom-up panoptic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 12475\u201312485."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_3_2_7_2","unstructured":"Bowen Cheng Alex Schwing and Alexander Kirillov. 2021. Per-pixel classification is not all you need for semantic segmentation. Advances in neural information processing systems 34 (2021) 17864\u201317875."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_3_2_9_2","first-page":"1","volume-title":"2023 International Joint Conference on Neural Networks (IJCNN)","author":"Fischedick S\u00f6hnke\u00a0Benedikt","year":"2023","unstructured":"S\u00f6hnke\u00a0Benedikt Fischedick, Daniel Seichter, Robin Schmidt, Leonard Rabes, and Horst-Michael Gross. 2023. Efficient multi-task scene analysis with rgb-d transformers. In 2023 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u201310."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Keke Geng Ge Dong Guodong Yin and Jingyu Hu. 2020. Deep dual-modal traffic objects instance segmentation method using camera and lidar data for autonomous driving. Remote Sensing 12 20 (2020) 3274.","DOI":"10.3390\/rs12203274"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"e_1_3_3_2_12_2","unstructured":"De-An Huang Zhiding Yu and Anima Anandkumar. 2022. Minvis: A minimal video instance segmentation framework without video-based training. Advances in Neural Information Processing Systems 35 (2022) 31265\u201331277."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00988"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"e_1_3_3_2_15_2","first-page":"16","volume-title":"2018 15th Conference on Computer and Robot Vision (CRV)","author":"Ku Jason","year":"2018","unstructured":"Jason Ku, Ali Harakeh, and Steven\u00a0L Waslander. 2018. In defense of classical image processing: Fast depth completion on the cpu. In 2018 15th Conference on Computer and Robot Vision (CRV). IEEE, 16\u201322."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"e_1_3_3_2_17_2","first-page":"1097","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Li Junlong","year":"2023","unstructured":"Junlong Li, Bingyao Yu, Yongming Rao, Jie Zhou, and Jiwen Lu. 2023. Tcovis: Temporally consistent online video instance segmentation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 1097\u20131107."},{"key":"e_1_3_3_2_18_2","first-page":"18847","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li Xiangtai","year":"2022","unstructured":"Xiangtai Li, Wenwei Zhang, Jiangmiao Pang, Kai Chen, Guangliang Cheng, Yunhai Tong, and Chen\u00a0Change Loy. 2022. Video k-net: A simple, strong, and unified baseline for video segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18847\u201318857."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","first-page":"4953","DOI":"10.1109\/ICRA48891.2023.10160315","volume-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","author":"Sodano Matteo","year":"2023","unstructured":"Matteo Sodano, Federico Magistri, Tiziano Guadagnino, Jens Behley, and Cyrill Stachniss. 2023. Robust double-encoder network for rgb-d panoptic segmentation. In 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 4953\u20134959."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Zhangjing Wang Yu Wu and Qingqing Niu. 2019. Multi-sensor fusion in automated driving: A survey. Ieee Access 8 (2019) 2847\u20132868.","DOI":"10.1109\/ACCESS.2019.2962554"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"e_1_3_3_2_23_2","unstructured":"Haofei Xu Jing Zhang Jianfei Cai Hamid Rezatofighi Fisher Yu Dacheng Tao and Andreas Geiger. 2023. Unifying flow stereo and depth estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Jiaming Zhang Huayao Liu Kailun Yang Xinxin Hu Ruiping Liu and Rainer Stiefelhagen. 2023. CMX: Cross-modal fusion for RGB-X semantic segmentation with transformers. IEEE Transactions on intelligent transportation systems (2023).","DOI":"10.1109\/TITS.2023.3300537"}],"event":{"name":"ICEA 2024: The 2024 International Conference on Intelligent Computing and its Emerging Applicaton","location":"Tokyo Japan","acronym":"ICEA 2024"},"container-title":["Proceedings of the 2024 International Conference on Intelligent Computing and its Emerging Applicaton"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3732437.3732763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T10:34:29Z","timestamp":1760438069000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3732437.3732763"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,28]]},"references-count":23,"alternative-id":["10.1145\/3732437.3732763","10.1145\/3732437"],"URL":"https:\/\/doi.org\/10.1145\/3732437.3732763","relation":{},"subject":[],"published":{"date-parts":[[2024,11,28]]},"assertion":[{"value":"2025-10-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}