{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:42:05Z","timestamp":1765309325691,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":89,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62472046"],"award-info":[{"award-number":["62472046"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754865","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"111-120","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8509-2452","authenticated-orcid":false,"given":"Xiaojian","family":"Lin","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8916-6944","authenticated-orcid":false,"given":"Wenxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4688-1380","authenticated-orcid":false,"given":"Yuchu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8404-9489","authenticated-orcid":false,"given":"Wangyu","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7983-8472","authenticated-orcid":false,"given":"Yiran","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2260-7772","authenticated-orcid":false,"given":"Kangxu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6909-1587","authenticated-orcid":false,"given":"Zongzheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2131-3044","authenticated-orcid":false,"given":"Guijin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4855-2464","authenticated-orcid":false,"given":"Lei","family":"Jin","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7903-581X","authenticated-orcid":false,"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2021.100164"},{"key":"e_1_3_2_1_2_1","unstructured":"Aduen Benjumea Izzeddin Teeti Fabio Cuzzolin and Andrew Bradley. 2021. YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles. https:\/\/arxiv.org\/abs\/2112.11798. arXiv preprint arXiv:2112.11798."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01808-8"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2993926"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00677"},{"key":"e_1_3_2_1_8_1","volume-title":"Bu Jin, Chonghao Sima, Wuqiang Zhang, Xiaohui Li, Paul Barsch, Hongyang Li, and Hao Zhao.","author":"Ding Kairui","year":"2024","unstructured":"Kairui Ding, Boyuan Chen, Yuchen Su, Huan ang Gao, Bu Jin, Chonghao Sima, Wuqiang Zhang, Xiaohui Li, Paul Barsch, Hongyang Li, and Hao Zhao. 2024. Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving. arXiv preprint arXiv:2409.06702 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0261-2"},{"key":"e_1_3_2_1_10_1","volume-title":"Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation","author":"Feng Yifan","year":"2024","unstructured":"Yifan Feng, Jiangang Huang, Shaoyi Du, Shihui Ying, Jun-Hai Yong, Yipeng Li, Guiguang Ding, Rongrong Ji, and Yue Gao. 2024. Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024). Early Access."},{"key":"e_1_3_2_1_11_1","unstructured":"Daiheng Gao Shilin Lu Shaw Walters Wenbo Zhou Jiaming Chu Jie Zhang Bang Zhang Mengxi Jia Jian Zhao Zhaoxin Fan et al. 2024a. EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers. arXiv preprint arXiv:2412.20413 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3345271"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7036-7045","author":"Ghiasi Golnaz","key":"e_1_3_2_1_14_1","unstructured":"Golnaz Ghiasi, Tsung-Yi Lin, and Quoc V. Le. 2019. NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7036-7045."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2437384"},{"key":"e_1_3_2_1_16_1","unstructured":"Jocher Glenn. 2023. Yolov8. https:\/\/github.com\/ultralytics\/ultralytics\/tree\/main. Accessed: 2025-03-02."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_3"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111174"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2021.100057"},{"key":"e_1_3_2_1_20_1","volume-title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv preprint arXiv:1704.04861 (2017). https:\/\/arxiv.org\/abs\/1704.04861"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125653"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"e_1_3_2_1_23_1","first-page":"550","article-title":"AlignSeg: Feature-Aligned Segmentation Networks","volume":"44","author":"Huang Zilong","year":"2021","unstructured":"Zilong Huang, Yunchao Wei, Xinggang Wang, Wenyu Liu, Thomas S. Huang, and Humphrey Shi. 2021b. AlignSeg: Feature-Aligned Segmentation Networks. IEEE Transactions Pattern Analysis and Machine Intelligence, Vol. 44, 1 (2021), 550-557.","journal-title":"IEEE Transactions Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00556"},{"key":"e_1_3_2_1_25_1","volume-title":"European Conference on Computer Vision (ECCV). Springer Nature Switzerland, Cham, 367-384","author":"Jin Bu","year":"2024","unstructured":"Bu Jin, Yupeng Zheng, Pengfei Li, Weize Li, Yuhang Zheng, Sujie Hu, Xinyu Liu, Jinwei Zhu, Zhijie Yan, Haiyang Sun, Kun Zhan, Peng Jia, Xiaoxiao Long, Yilun Chen, and Hao Zhao. 2024. TOD^3Cap: Towards 3D Dense Captioning in Outdoor Scenes. In European Conference on Computer Vision (ECCV). Springer Nature Switzerland, Cham, 367-384."},{"key":"e_1_3_2_1_26_1","volume-title":"Yolov11: An overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725","author":"Khanam Rahima","year":"2024","unstructured":"Rahima Khanam and Muhammad Hussain. 2024. Yolov11: An overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Set you straight: Auto-steering denoising trajectories to sidestep unwanted concepts. arXiv preprint arXiv:2504.12782","author":"Li Leyang","year":"2025","unstructured":"Leyang Li, Shilin Lu, Yan Ren, and Adams Wai-Kin Kong. 2025. Set you straight: Auto-steering denoising trajectories to sidestep unwanted concepts. arXiv preprint arXiv:2504.12782 (2025)."},{"key":"e_1_3_2_1_28_1","first-page":"17597","article-title":"TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation","volume":"35","author":"Li Pengfei","year":"2022","unstructured":"Pengfei Li, Beiwen Tian, Yongliang Shi, Xiaoxue Chen, Hao Zhao, Guyue Zhou, and Ya-Qin Zhang. 2022. TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 35. 17597-17611.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_29_1","volume-title":"Sfnet: Faster and Accurate Semantic Segmentation via Semantic Flow. International Journal of Computer Vision","author":"Li Xiangtai","year":"2023","unstructured":"Xiangtai Li, Jiangning Zhang, Yibo Yang, Guangliang Cheng, Kuiyuan Yang, Yunhai Tong, and Dacheng Tao. 2023b. Sfnet: Faster and Accurate Semantic Segmentation via Semantic Flow. International Journal of Computer Vision (2023), 1-24."},{"key":"e_1_3_2_1_30_1","volume-title":"Understanding Embodied Reference with Touch-Line Transformer. In International Conference on Learning Representations (ICLR). https:\/\/yang-li-2000","author":"Li Yang","year":"2023","unstructured":"Yang Li, Xiaoxue Chen, Hao Zhao, Jiangtao Gong, Guyue Zhou, Federico Rossano, and Yixin Zhu. 2023a. Understanding Embodied Reference with Touch-Line Transformer. In International Conference on Learning Representations (ICLR). https:\/\/yang-li-2000.github.io\/Touch-Line-Transformer Conference paper."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of International Conference on Learning Representations. 1-12","author":"Li Zongyi","year":"2021","unstructured":"Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, and Anima Anandkumar. 2021. Fourier neural operator for parametric partial differential equations. In Proceedings of International Conference on Learning Representations. 1-12."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_33_1","first-page":"740","volume-title":"Zurich","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 International Publishing, 740-755."},{"key":"e_1_3_2_1_34_1","unstructured":"Xiaojian Lin and Michael Losavio. 2025. A Comprehensive Survey on Bias and Fairness in Generative AI: Legal Ethical and Technical Responses. https:\/\/ssrn.com\/abstract=5164147 Available at SSRN: https:\/\/ssrn.com\/abstract=5164147."},{"key":"e_1_3_2_1_35_1","volume-title":"Learning Spatial Fusion for Single-Shot Object Detection. arXiv preprint arXiv:1911.09516","author":"Liu Songtao","year":"2019","unstructured":"Songtao Liu, Di Huang, and Yunhong Wang. 2019. Learning Spatial Fusion for Single-Shot Object Detection. arXiv preprint arXiv:1911.09516 (2019)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"e_1_3_2_1_37_1","first-page":"21","volume-title":"Amsterdam, The Netherlands","author":"Liu Wei","year":"2016","unstructured":"Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. 2016. SSD: Single shot multibox detector. In In Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part I. Springer International Publishing, 21-37."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00293"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3052442"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00615"},{"key":"e_1_3_2_1_42_1","volume-title":"Robust watermarking using generative priors against image editing: From benchmarking to advances. arXiv preprint arXiv:2410.18775","author":"Lu Shilin","year":"2024","unstructured":"Shilin Lu, Zihan Zhou, Jiayou Lu, Yuanzhi Zhu, and Adams Wai-Kin Kong. 2024b. Robust watermarking using generative priors against image editing: From benchmarking to advances. arXiv preprint arXiv:2410.18775 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01488"},{"key":"e_1_3_2_1_44_1","volume-title":"Dual Refinement Feature Pyramid Networks for Object Detection. arXiv preprint arXiv:2012.01733","author":"Ma Jialiang","year":"2020","unstructured":"Jialiang Ma and Bin Chen. 2020. Dual Refinement Feature Pyramid Networks for Object Detection. arXiv preprint arXiv:2012.01733 (2020)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3284035"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00425"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2023.03.009"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00433"},{"volume-title":"Digital image processing algorithms and applications","author":"Pitas Ioannis","key":"e_1_3_2_1_49_1","unstructured":"Ioannis Pitas. 2000. Digital image processing algorithms and applications. John Wiley & Sons."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of International Conference on Machine Learning. 5301-5310","author":"Rahaman Nasim","year":"2019","unstructured":"Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, Fred A. Hamprecht, Yoshua Bengio, and Aaron Courville. 2019. On the spectral bias of neural networks. In Proceedings of International Conference on Machine Learning. 5301-5310."},{"key":"e_1_3_2_1_52_1","first-page":"980","article-title":"Global filter networks for image classification","volume":"34","author":"Rao Yongming","year":"2021","unstructured":"Yongming Rao, Wenliang Zhao, Zheng Zhu, Jiwen Lu, and Jie Zhou. 2021. Global filter networks for image classification. In Proceedings of Advances in Neural Information Processing Systems, Vol. 34. 980-993.","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_54_1","volume-title":"A-MESS: Anchor-based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition. In IEEE International Conference on Multimedia and Expo. IEEE","author":"Shen Yaomin","year":"2025","unstructured":"Yaomin Shen, XiaoJian Lin, and Wei Fan. 2025. A-MESS: Anchor-based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition. In IEEE International Conference on Multimedia and Expo. IEEE, Nantes, France. https:\/\/arxiv.org\/pdf\/2503.19474 To appear."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"Sakthitharan Subramanian Rajesh S. P. I. Britto and S. Sankaran. 2023. MDHO: mayfly deer hunting optimization algorithm for optimal obstacle avoidance based path planning using mobile robots. Cybernetics and Systems (2023) 1-20.","DOI":"10.1080\/01969722.2023.2177804"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120576"},{"key":"e_1_3_2_1_58_1","volume-title":"Unsupervised Road Anomaly Detection with Language Anchors. In 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 7778-7785","author":"Tian Beiwen","year":"2023","unstructured":"Beiwen Tian, Mingdao Liu, Huan ang Gao, Pengfei Li, Hao Zhao, and Guyue Zhou. 2023. Unsupervised Road Anomaly Detection with Language Anchors. In 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 7778-7785."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121811"},{"key":"e_1_3_2_1_60_1","volume-title":"Yolov12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524","author":"Tian Yunjie","year":"2025","unstructured":"Yunjie Tian, Qixiang Ye, and David Doermann. 2025. Yolov12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524 (2025)."},{"key":"e_1_3_2_1_61_1","volume-title":"Optimized sliding mode control based on cuckoo search algorithm: Application for 2df robot manipulator. Cybernetics and Systems","author":"Tilijani Hatem","year":"2023","unstructured":"Hatem Tilijani, Ameni Jouila, and Khaled Nouri. 2023. Optimized sliding mode control based on cuckoo search algorithm: Application for 2df robot manipulator. Cybernetics and Systems (2023), 1-17."},{"key":"e_1_3_2_1_62_1","first-page":"107984","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"Wang Ao","year":"2024","unstructured":"Ao Wang, Hui Chen, Lihao Liu, Zija Lin, Jungong Han, and Guiguang Ding. 2024a. Yolov10: Real-time end-to-end object detection. Advances in Neural Information Processing Systems, Vol. 37 (2024), 107984-108011.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_63_1","first-page":"51094","article-title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","volume":"36","author":"Wang Chengcheng","year":"2023","unstructured":"Chengcheng Wang, Wenwei He, Yifan Nie, Jianyuan Guo, Chang Liu, Yufei Wang, and Kai Han. 2023a. Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism. In Advances in Neural Information Processing Systems, Vol. 36. 51094-51112.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_64_1","volume-title":"European Conference on Computer Vision (ECCV). Springer Nature Switzerland, Cham, 1-21","author":"Wang Chien-Yao","year":"2024","unstructured":"Chien-Yao Wang, I-Hau Yeh, and Hong-Yuan Mark Liao. 2024b. Yolov9: Learning what you want to learn using programmable gradient information. In European Conference on Computer Vision (ECCV). Springer Nature Switzerland, Cham, 1-21."},{"volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 8684-8694","author":"Wang Haohan","key":"e_1_3_2_1_65_1","unstructured":"Haohan Wang, Xindi Wu, Zeyi Huang, and Eric P. Xing. 2020. High-frequency component helps explain the generalization of convolutional neural networks. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 8684-8694."},{"key":"e_1_3_2_1_66_1","first-page":"4674","article-title":"CARAFE: Unified Content-Aware ReAssembly of Features","volume":"44","author":"Wang Jiaqian","year":"2021","unstructured":"Jiaqian Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, and Dahua Lin. 2021. CARAFE: Unified Content-Aware ReAssembly of Features. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 9 (2021), 4674-4687.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3525725"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3526056"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105504"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121848"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1339-y"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3286943"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17261"},{"key":"e_1_3_2_1_75_1","volume-title":"Proceedings of Advances in Neural Information Processing Systems","volume":"32","author":"Yin Dong","year":"2019","unstructured":"Dong Yin, Raphael Gontijo Lopes, Jonathon Shlens, Ekin D. Cubuk, and Justin Gilmer. 2019. A Fourier perspective on model robustness in computer vision. In Proceedings of Advances in Neural Information Processing Systems, Vol. 32."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.07.003"},{"volume-title":"Proceedings of European Conference on Computer Vision. 818-833","author":"Matthew","key":"e_1_3_2_1_79_1","unstructured":"Matthew D. Zeiler and Rob Fergus. 2014. Visualizing and Understanding Convolutional Networks. In Proceedings of European Conference on Computer Vision. 818-833."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"e_1_3_2_1_81_1","volume-title":"Detect Anything 3D in the Wild. arXiv preprint arXiv:2504.07958","author":"Zhang Hanxue","year":"2025","unstructured":"Hanxue Zhang, Haoran Jiang, Qingsong Yao, Yanan Sun, Renrui Zhang, Hao Zhao, Hongyang Li, Hongzi Zhu, and Zetong Yang. 2025a. Detect Anything 3D in the Wild. arXiv preprint arXiv:2504.07958 (2025). https:\/\/github.com\/OpenDriveLab\/DetAny3D"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102814"},{"key":"e_1_3_2_1_83_1","volume-title":"Proceedings of International Conference on Machine Learning. 7324-7334","author":"Zhang Richard","year":"2019","unstructured":"Richard Zhang. 2019. Making convolutional networks shift-invariant again. In Proceedings of International Conference on Machine Learning. 7324-7334."},{"key":"e_1_3_2_1_84_1","volume-title":"Proceedings of the International Joint Conference on Neural Networks (IJCNN). https:\/\/arxiv.org\/abs\/2504","author":"Zhang Wenxin","year":"2025","unstructured":"Wenxin Zhang, Xiaojian Lin, Wenjun Yu, Guangzhen Yao, Jingxing Zhong, Yu Li, Renda Han, Songcheng Xu, Hao Shi, and Cuicui Luo. 2025b. DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detection. In Proceedings of the International Joint Conference on Neural Networks (IJCNN). https:\/\/arxiv.org\/abs\/2504.14204 To appear."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-9921-6_2"},{"key":"e_1_3_2_1_86_1","volume-title":"Proceedings of the International Joint Conference on Neural Networks (IJCNN). https:\/\/arxiv.org\/abs\/2504","author":"Zhang Wenxin","year":"2025","unstructured":"Wenxin Zhang, Jingxing Zhong, Guangzhen Yao, Renda Han, Xiaojian Lin, Lei Jiang, Zeyu Zhang, and Cuicui Luo. 2025 e. Dual-channel Heterophilic Message Passing for Graph Fraud Detection. In Proceedings of the International Joint Conference on Neural Networks (IJCNN). https:\/\/arxiv.org\/abs\/2504.14205 To appear."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00276"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVRIS.2019.00110"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01672-y"}],"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\/3746027.3754865","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:39:56Z","timestamp":1765309196000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754865"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":89,"alternative-id":["10.1145\/3746027.3754865","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754865","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"}}]}}