{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:10:01Z","timestamp":1765343401506,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"name":"Sustainable Urban Transport Intelligence Ministry of Engineering Research Center Open Fund Project","award":["KCX2024-KF01"],"award-info":[{"award-number":["KCX2024-KF01"]}]},{"name":"Research and Practice of Software Engineering?a key technology project for intelligent rural development on the Qinghai-Tibet Plateau","award":["2024CXTD09"],"award-info":[{"award-number":["2024CXTD09"]}]},{"name":"Sichuan Science and Technology Program","award":["2023YFN0026"],"award-info":[{"award-number":["2023YFN0026"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754710","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"2673-2682","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["OoDDINO: A Multi-level Framework for Anomaly Segmentation on Complex Road Scenes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9160-9234","authenticated-orcid":false,"given":"Yuxing","family":"Liu","sequence":"first","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Southwest Minzu University, chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9132-1621","authenticated-orcid":false,"given":"Ji","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Southwest Minzu University, Chengdu, Sichuan, China and Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4395-7801","authenticated-orcid":false,"given":"Xuchuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Southwest Minzu University, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2257-7981","authenticated-orcid":false,"given":"Jingzhong","family":"Xiao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Southwest Minzu University, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3446-2406","authenticated-orcid":false,"given":"Huimin","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Southwest Minzu University, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6474-7582","authenticated-orcid":false,"given":"Jiaxin","family":"Zhong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Southwest Minzu University, chengdu, Sichuan, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01541"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01511-6"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_5_1","volume-title":"Segmentmeifyoucan: A benchmark for anomaly segmentation. ARXIV","author":"Chan Robin","year":"2021","unstructured":"Robin Chan, Krzysztof Lis, Svenja Uhlemeyer, Hermann Blum, Sina Honari, Roland Siegwart, Pascal Fua, Mathieu Salzmann, and Matthias Rottmann. 2021. Segmentmeifyoucan: A benchmark for anomaly segmentation. ARXIV (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547943"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.","author":"Biase Giancarlo Di","key":"e_1_3_2_1_8_1","unstructured":"Giancarlo Di Biase, Hermann Blum, Roland Y. Siegwart, and C\u00e9sar Cadena. 2021. Pixel-Wise Anomaly Detection in Complex Driving Scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the International Conference on Machine Learning. 1050-1059","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In Proceedings of the International Conference on Machine Learning. 1050-1059."},{"key":"e_1_3_2_1_10_1","volume-title":"Clip-adapter: Better vision-language models with feature adapters. ARXIV","author":"Gao P.","year":"2021","unstructured":"P. Gao, S. Geng, R. Zhang, T. Ma, R. Fang, Y. Zhang, H. Li, and Y. Qiao. 2021. Clip-adapter: Better vision-language models with feature adapters. ARXIV (2021)."},{"key":"e_1_3_2_1_11_1","volume-title":"Dense Anomaly Detection by Robust Learning on Synthetic Negative Data. ARXIV","author":"Grcic Matej","year":"2021","unstructured":"Matej Grcic, Petra Bevandi\u0107, and Sini\u0161a \u0160egvi\u0107. 2021. Dense Anomaly Detection by Robust Learning on Synthetic Negative Data. ARXIV (2021)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_29"},{"key":"e_1_3_2_1_13_1","volume-title":"Open-vocabulary object detection via vision and language knowledge distillation. Learning","author":"Gu Xiuye","year":"2021","unstructured":"Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo, and Yin Cui. 2021. Open-vocabulary object detection via vision and language knowledge distillation. Learning (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"Damo-streamnet: Optimizing streaming perception in autonomous driving. ARXIV","author":"He Jun-Yan","year":"2023","unstructured":"Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Wangmeng Xiang, Binghui Chen, Bin Luo, Yifeng Geng, and Xuansong Xie. 2023. Damo-streamnet: Optimizing streaming perception in autonomous driving. ARXIV (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00013"},{"key":"e_1_3_2_1_16_1","volume-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks. ARXIV","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. A baseline for detecting misclassified and out-of-distribution examples in neural networks. ARXIV (2016)."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Hendrycks Dan","year":"2017","unstructured":"Dan Hendrycks and Kevin Gimpel. 2017a. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Hendrycks Dan","year":"2017","unstructured":"Dan Hendrycks and Kevin Gimpel. 2017b. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01598"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5830-5840","author":"Joseph K. J.","key":"e_1_3_2_1_20_1","unstructured":"K. J. Joseph, S. Khan, F. S. Khan, and V. N. Balasubramanian. 2021. Towards Open World Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5830-5840."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01514"},{"key":"e_1_3_2_1_22_1","volume-title":"NIPS","volume":"30","author":"Kendall Alex","year":"2017","unstructured":"Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in bayesian deep learning for computer vision? NIPS, Vol. 30 (2017)."},{"volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Kingma D.P.","key":"e_1_3_2_1_23_1","unstructured":"D.P. Kingma and J. Ba. 2017. Adam: A Method for Stochastic Optimization. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","first-page":"6402","article-title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","author":"Lakshminarayanan Balaji","year":"2017","unstructured":"Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. In Proceedings of the Advances in Neural Information Processing Systems. 6402-6413.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094971"},{"key":"e_1_3_2_1_26_1","volume-title":"NIPS","volume":"31","author":"Lee Kimin","year":"2018","unstructured":"Kimin Lee, Kibok Lee, Honglak Lee, and Jinwoo Shin. 2018. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. NIPS, Vol. 31 (2018)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094855"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00926"},{"key":"e_1_3_2_1_29_1","volume-title":"GMMSeg: Gaussian Mixture Based Generative Semantic Segmentation Models. ARXIV","author":"Liang Chen","year":"2022","unstructured":"Chen Liang, Wenguan Wang, Jiaxu Miao, and Yi Yang. 2022. GMMSeg: Gaussian Mixture Based Generative Semantic Segmentation Models. ARXIV (2022)."},{"key":"e_1_3_2_1_30_1","volume-title":"Detecting Road Obstacles by Erasing Them. ARXIV","author":"Lis Krzysztof","year":"2020","unstructured":"Krzysztof Lis, Sina Honari, Pascal Fua, and Mathieu Salzmann. 2020. Detecting Road Obstacles by Erasing Them. ARXIV (2020)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00224"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the European Conference on Computer Vision. 38-55","author":"Liu Shilong","year":"2024","unstructured":"Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, et al., 2024. Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection. In Proceedings of the European Conference on Computer Vision. 38-55."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00112"},{"key":"e_1_3_2_1_34_1","volume-title":"Russ R Salakhutdinov, Louis-Philippe Morency, and Masahito Ueda.","author":"Liu Ziyin","year":"2019","unstructured":"Ziyin Liu, Zhikang Wang, Paul Pu Liang, Russ R Salakhutdinov, Louis-Philippe Morency, and Masahito Ueda. 2019. Deep Gamblers: Learning to Abstain with Portfolio Theory. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 32."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2018","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Decoupled weight decay regularization. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_37_1","first-page":"215","article-title":"Uncertainty for identifying open-set errors in visual object detection","volume":"7","author":"Miller Dimity","year":"2021","unstructured":"Dimity Miller, Niko S\u00fcnderhauf, Michael Milford, and Feras Dayoub. 2021. Uncertainty for identifying open-set errors in visual object detection. RAL, Vol. 7, 1 (2021), 215-222.","journal-title":"RAL"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00072"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547786"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3029006"},{"key":"e_1_3_2_1_42_1","volume-title":"Mask2anomaly: Mask transformer for universal open-set segmentation","author":"Rai Shyam Nandan","year":"2024","unstructured":"Shyam Nandan Rai, Fabio Cermelli, Barbara Caputo, and Carlo Masone. 2024. Mask2anomaly: Mask transformer for universal open-set segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_15"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01536"},{"key":"e_1_3_2_1_45_1","first-page":"7597","article-title":"Multimodal Anomaly Detection via Contrastive Fusion","volume":"33","author":"Wang Wei","year":"2022","unstructured":"Wei Wang, Zhiqiang Chen, Xu Tao, Yi Cao, Liang Cheng, and Cheng Deng. 2022. Multimodal Anomaly Detection via Contrastive Fusion. IEEE Transactions on Neural Networks and Learning Systems, Vol. 33, 12 (2022), 7597-7610.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_9"},{"key":"e_1_3_2_1_47_1","volume-title":"Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection. ARXIV","author":"Yao Lewei","year":"2022","unstructured":"Lewei Yao, Jianyuan Han, Yizeng Wen, Xiaodan Liang, Dan Xu, Wei Zhang, Zhen Li, Chunjing Xu, and Hang Xu. 2022. Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection. ARXIV (2022)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611849"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00375"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Mi Zheng Guanglei Yang Zitong Huang Zhenhua Guo Kevin Han and Wangmeng Zuo. 2025. Segmenting Objectiveness and Task-awareness Unknown Region for Autonomous Driving. arXiv:2504.19183 [cs.CV] https:\/\/arxiv.org\/abs\/2504.19183","DOI":"10.1145\/3746027.3755178"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:06:12Z","timestamp":1765343172000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754710"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":52,"alternative-id":["10.1145\/3746027.3754710","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754710","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}