{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:08:41Z","timestamp":1765357721407,"version":"3.41.0"},"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Program of China","award":["No. 2018YFB0204301"],"award-info":[{"award-number":["No. 2018YFB0204301"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"Natural Science Foundation of Hunan Province of China","doi-asserted-by":"publisher","award":["No. 2022JJ30666"],"award-info":[{"award-number":["No. 2022JJ30666"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680583","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"9067-9076","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Sniffing Threatening Open-World Objects in Autonomous Driving by Open-Vocabulary Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1380-1088","authenticated-orcid":false,"given":"Yulin","family":"He","sequence":"first","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7985-6492","authenticated-orcid":false,"given":"Siqi","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2876-6687","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6654-3750","authenticated-orcid":false,"given":"Tianci","family":"Xun","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1233-5679","authenticated-orcid":false,"given":"Yusong","family":"Tan","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"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\/ICME55011.2023.00381"},{"key":"e_1_3_2_1_3_1","unstructured":"Kai Chen Jiaqi Wang Jiangmiao Pang Yuhang Cao Yu Xiong Xiaoxiao Li Shuyang Sun Wansen Feng Ziwei Liu Jiarui Xu et al. 2019. MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_1_5_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_6_1","volume-title":"SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving","author":"Ding Ning","year":"2023","unstructured":"Ning Ding, Ce Zhang, and Azim Eskandarian. 2023. SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving. IEEE Transactions on Intelligent Vehicles (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Learning Representations.","author":"Du Xuefeng","year":"2021","unstructured":"Xuefeng Du, Zhaoning Wang, Mu Cai, and Yixuan Li. 2021. VOS: Learning What You Don't Know by Virtual Outlier Synthesis. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"e_1_3_2_1_9_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Han Jianhua","year":"2021","unstructured":"Jianhua Han, Xiwen Liang, Hang Xu, Kai Chen, HONG Lanqing, Jiageng Mao, Chaoqiang Ye, Wei Zhang, Zhenguo Li, Xiaodan Liang, et al. 2021. SODA10M: A Large-Scale 2D Self\/Semi-Supervised Object Detection Dataset for Autonomous Driving. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_1_10_1","volume-title":"Pascal VOC 2008 challenge. World Literature Today","volume":"24","author":"Hoiem Derek","year":"2009","unstructured":"Derek Hoiem, Santosh K Divvala, and James H Hays. 2009. Pascal VOC 2008 challenge. World Literature Today, Vol. 24, 1 (2009), 1--4."},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Machine Learning. PMLR, 2790--2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790--2799."},{"key":"e_1_3_2_1_12_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","volume-title":"Multi-modal sensor fusion for auto driving perception: A survey. arXiv preprint arXiv:2202.02703","author":"Huang Keli","year":"2022","unstructured":"Keli Huang, Botian Shi, Xiang Li, Xin Li, Siyuan Huang, and Yikang Li. 2022. Multi-modal sensor fusion for auto driving perception: A survey. arXiv preprint arXiv:2202.02703 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"International conference on machine learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904--4916."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Learning Representations.","author":"Kumar Ananya","year":"2021","unstructured":"Ananya Kumar, Aditi Raghunathan, Robbie Matthew Jones, Tengyu Ma, and Percy Liang. 2021. Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_18_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Kuo Weicheng","year":"2022","unstructured":"Weicheng Kuo, Yin Cui, Xiuye Gu, AJ Piergiovanni, and Anelia Angelova. 2022. Open-Vocabulary Object Detection upon Frozen Vision and Language Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","first-page":"9287","article-title":"Elevater: A benchmark and toolkit for evaluating language-augmented visual models","volume":"35","author":"Li Chunyuan","year":"2022","unstructured":"Chunyuan Li, Haotian Liu, Liunian Li, Pengchuan Zhang, Jyoti Aneja, Jianwei Yang, Ping Jin, Houdong Hu, Zicheng Liu, Yong Jae Lee, et al. 2022. Elevater: A benchmark and toolkit for evaluating language-augmented visual models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 9287--9301.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_24"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"e_1_3_2_1_22_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_3_2_1_23_1","volume-title":"A survey of knowledge graph reasoning on graph types: Static, dynamic, and multi-modal","author":"Liang Ke","year":"2024","unstructured":"Ke Liang, Lingyuan Meng, Meng Liu, Yue Liu, Wenxuan Tu, Siwei Wang, Sihang Zhou, Xinwang Liu, Fuchun Sun, and Kunlun He. 2024. A survey of knowledge graph reasoning on graph types: Static, dynamic, and multi-modal. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Structure guided multi-modal pre-trained transformer for knowledge graph reasoning. arXiv preprint arXiv:2307.03591","author":"Liang Ke","year":"2023","unstructured":"Ke Liang, Sihang Zhou, Yue Liu, Lingyuan Meng, Meng Liu, and Xinwang Liu. 2023. Structure guided multi-modal pre-trained transformer for knowledge graph reasoning. arXiv preprint arXiv:2307.03591 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00315"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Liu Shilong","year":"2024","unstructured":"Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, et al. 2024. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. Proceedings of the European Conference on Computer Vision (ECCV) (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2018","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01885"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548165"},{"volume-title":"Psychology of learning and motivation.","author":"McCloskey Michael","key":"e_1_3_2_1_32_1","unstructured":"Michael McCloskey and Neal J Cohen. 1989. Catastrophic interference in connectionist networks: The sequential learning problem. In Psychology of learning and motivation. Vol. 24. Elsevier, 109--165."},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_34_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"e_1_3_2_1_36_1","volume-title":"Proc. NeurIPS Workshops.","author":"Singh Deepak Kumar","year":"2021","unstructured":"Deepak Kumar Singh, Shyam Nandan Rai, KJ Joseph, Rohit Saluja, Vineeth N Balasubramanian, Chetan Arora, Anbumani Subramanian, and CV Jawahar. 2021. ORDER: Open World Object Detection on Road Scenes. In Proc. NeurIPS Workshops."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_12"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"e_1_3_2_1_42_1","volume-title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. In The Eleventh International Conference on Learning Representations.","author":"Zhang Hao","year":"2022","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel Ni, and Heung-Yeung Shum. 2022. DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Zhu Xizhou","year":"2021","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2021. Deformable detr: Deformable transformers for end-to-end object detection. Proceedings of the International Conference on Learning Representations (ICLR) (2021)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01101"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680583","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680583"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":44,"alternative-id":["10.1145\/3664647.3680583","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680583","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"}}]}}