{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T15:55:52Z","timestamp":1781366152257,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Science and Technology Council","award":["114-2218-E-035-001"],"award-info":[{"award-number":["114-2218-E-035-001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,11]]},"DOI":"10.1145\/3803291.3803339","type":"proceedings-article","created":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T15:29:06Z","timestamp":1781364546000},"page":"241-246","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Training-Free Approach to Long-Tail Object Detection for Autonomous Driving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6735-0473","authenticated-orcid":false,"given":"Yu-Chen","family":"Lin","sequence":"first","affiliation":[{"name":"Automatic Control Engineering, Feng Chia University, Taichung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9411-6690","authenticated-orcid":false,"given":"Quoc-Thang","family":"Phan","sequence":"additional","affiliation":[{"name":"Automatic Control Engineering, Feng Chia University, Taichung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2015-5256","authenticated-orcid":false,"given":"Wen-Hui","family":"Chen","sequence":"additional","affiliation":[{"name":"Graduate Institute of Automation Technology, National Taipei University of Technology, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,13]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Zhaowei Cai and Nuno Vasconcelos. 2017. Cascade R-CNN: Delving into High Quality Object Detection. 10.48550\/arXiv.1712.00726arXiv:https:\/\/arXiv.org\/abs\/1712.00726.","DOI":"10.48550\/arXiv.1712.00726"},{"key":"e_1_3_3_1_3_2","unstructured":"Li Chen Penghao Wu Kashyap Chitta Bernhard Jaeger Andreas Geiger and Hongyang Li. 2024. End-to-end Autonomous Driving: Challenges and Frontiers. http:\/\/arxiv.org\/abs\/2306.16927 arXiv:https:\/\/arXiv.org\/abs\/2306.16927."},{"key":"e_1_3_3_1_4_2","unstructured":"COCO Consortium. [n.d.]. pycocotools: Official COCO Evaluation API. https:\/\/github.com\/cocodataset\/cocoapi. Accessed: April 9 2025."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093355"},{"key":"e_1_3_3_1_7_2","unstructured":"Haoxiang Gao Zhongruo Wang Yaqian Li Kaiwen Long Ming Yang and Yiqing Shen. 2024. A Survey for Foundation Models in Autonomous Driving. http:\/\/arxiv.org\/abs\/2402.01105 arXiv:https:\/\/arXiv.org\/abs\/2402.01105 [cs]."},{"key":"e_1_3_3_1_8_2","unstructured":"Xiuye Gu Tsung-Yi Lin Weicheng Kuo and Yin Cui. 2021. Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.13921 (2021)."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Kaican Li Kai Chen Haoyu Wang Lanqing Hong Chaoqiang Ye Jianhua Han Yukuai Chen Wei Zhang Chunjing Xu Dit-Yan Yeung Xiaodan Liang Zhenguo Li and Hang Xu. 2022. CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving. 10.48550\/arXiv.2203.07724arXiv:https:\/\/arXiv.org\/abs\/2203.07724.","DOI":"10.48550\/arXiv.2203.07724"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Yiming Li Yi Wang Wenqian Wang Dan Lin Bingbing Li and Kim-Hui Yap. 2024. Open World Object Detection: A Survey. 10.48550\/arXiv.2410.11301arXiv:https:\/\/arXiv.org\/abs\/2410.11301.","DOI":"10.48550\/arXiv.2410.11301"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Qing Jiang Chunyuan Li Jianwei Yang Hang Su Jun Zhu and Lei Zhang. 2024. Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection. 10.48550\/arXiv.2303.05499arXiv:https:\/\/arXiv.org\/abs\/2303.05499.","DOI":"10.48550\/arXiv.2303.05499"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Ze Liu Yutong Lin Yue Cao Han Hu Yixuan Wei Zheng Zhang Stephen Lin and Baining Guo. 2021. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. 10.48550\/arXiv.2103.14030arXiv:https:\/\/arXiv.org\/abs\/2103.14030.","DOI":"10.48550\/arXiv.2103.14030"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Zhuang Liu Hanzi Mao Chao-Yuan Wu Christoph Feichtenhofer Trevor Darrell and Saining Xie. 2022. A ConvNet for the 2020s. 10.48550\/arXiv.2201.03545arXiv:https:\/\/arXiv.org\/abs\/2201.03545.","DOI":"10.48550\/arXiv.2201.03545"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Matthias Minderer Alexey Gritsenko and Neil Houlsby. 2024. Scaling Open-Vocabulary Object Detection. 10.48550\/arXiv.2306.09683arXiv:https:\/\/arXiv.org\/abs\/2306.09683.","DOI":"10.48550\/arXiv.2306.09683"},{"key":"e_1_3_3_1_16_2","unstructured":"Zach Nussbaum John\u00a0Xavier Morris Andriy Mulyar and Brandon Duderstadt. 2025. Nomic Embed: Training a Reproducible Long Context Text Embedder. Transactions on Machine Learning Research (2025). https:\/\/openreview.net\/forum?id=IPmzyQSiQE Reproducibility Certification."},{"key":"e_1_3_3_1_17_2","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. http:\/\/arxiv.org\/abs\/2103.00020 arXiv:https:\/\/arXiv.org\/abs\/2103.00020."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2016. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. 10.48550\/arXiv.1506.01497arXiv:https:\/\/arXiv.org\/abs\/1506.01497.","DOI":"10.48550\/arXiv.1506.01497"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Walter\u00a0J Scheirer Anderson de Rezende\u00a0Rocha Archana Sapkota and Terrance\u00a0E Boult. 2012. Toward open set recognition. IEEE transactions on pattern analysis and machine intelligence 35 7 (2012) 1757\u20131772.","DOI":"10.1109\/TPAMI.2012.256"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Roman Solovyev Weimin Wang and Tatiana Gabruseva. 2021. Weighted boxes fusion: Ensembling boxes from different object detection models. Image and Vision Computing 107 (March 2021) 104117. 10.1016\/j.imavis.2021.104117arXiv:https:\/\/arXiv.org\/abs\/1910.13302 [cs].","DOI":"10.1016\/j.imavis.2021.104117"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647363"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Jingyi Zhang Jiaxing Huang Sheng Jin and Shijian Lu. 2024. Vision-language models for vision tasks: A survey. IEEE transactions on pattern analysis and machine intelligence 46 8 (2024) 5625\u20135644.","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","unstructured":"Tiancheng Zhao Peng Liu Xuan He Lu Zhang and Kyusong Lee. 2024. Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head. 10.48550\/arXiv.2403.06892arXiv:https:\/\/arXiv.org\/abs\/2403.06892.","DOI":"10.48550\/arXiv.2403.06892"},{"key":"e_1_3_3_1_24_2","unstructured":"Yian Zhao Wenyu Lv Shangliang Xu Jinman Wei Guanzhong Wang Qingqing Dang Yi Liu and Jie Chen. 2024. DETRs Beat YOLOs on Real-time Object Detection. http:\/\/arxiv.org\/abs\/2304.08069 arXiv:https:\/\/arXiv.org\/abs\/2304.08069."},{"key":"e_1_3_3_1_25_2","unstructured":"Xingcheng Zhou Mingyu Liu Ekim Yurtsever Bare\u00a0Luka Zagar Walter Zimmer Hu Cao and Alois\u00a0C. Knoll. 2024. Vision Language Models in Autonomous Driving: A Survey and Outlook. http:\/\/arxiv.org\/abs\/2310.14414 arXiv:https:\/\/arXiv.org\/abs\/2310.14414."}],"event":{"name":"ICICT 2026: 2026 The 9th International Conference on Information and Computer Technologies","location":"Honolulu , HI , USA","acronym":"ICICT 2026"},"container-title":["Proceedings of the 2026 9th International Conference on Information and Computer Technologies"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3803291.3803339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T15:31:43Z","timestamp":1781364703000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3803291.3803339"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,11]]},"references-count":24,"alternative-id":["10.1145\/3803291.3803339","10.1145\/3803291"],"URL":"https:\/\/doi.org\/10.1145\/3803291.3803339","relation":{},"subject":[],"published":{"date-parts":[[2026,3,11]]},"assertion":[{"value":"2026-06-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}