{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:00:07Z","timestamp":1765339207845,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376233,62176224,62176092,62222602,62306165,62306165"],"award-info":[{"award-number":["62376233,62176224,62176092,62222602,62306165,62306165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology on Sonar Laboratory","award":["2024-JCJQ-LB-32\/07"],"award-info":[{"award-number":["2024-JCJQ-LB-32\/07"]}]},{"name":"China Academy of RailwaySciences","award":["2023Y1357"],"award-info":[{"award-number":["2023Y1357"]}]},{"name":"Xiaomi Young Talents Program"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754890","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"2929-2938","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3481-4159","authenticated-orcid":false,"given":"Jiahao","family":"Li","sequence":"first","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3497-9611","authenticated-orcid":false,"given":"Yang","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6153-5004","authenticated-orcid":false,"given":"Yachao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4429-0176","authenticated-orcid":false,"given":"Fangyong","family":"Wang","sequence":"additional","affiliation":[{"name":"Hanjiang National Laboratory, Wuhan, HuBei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6945-7437","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8926-4162","authenticated-orcid":false,"given":"Yanyun","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Zero-shot semantic segmentation. Advances in Neural Information Processing Systems 32","author":"Bucher Maxime","year":"2019","unstructured":"Maxime Bucher, Tuan-Hung Vu, Matthieu Cord, and Patrick P\u00e9rez. 2019. Zero-shot semantic segmentation. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings, Part III 16","author":"Chen Guangyao","year":"2020","unstructured":"Guangyao Chen, Limeng Qiao, Yemin Shi, Peixi Peng, Jia Li, Tiejun Huang, Shiliang Pu, and Yonghong Tian. 2020. Learning open set network with discriminative reciprocal points. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part III 16. Springer, 507--522."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00942"},{"key":"e_1_3_2_1_5_1","volume-title":"Paul Hongsuck Seo, and Seungryong Kim","author":"Cho Seokju","year":"2023","unstructured":"Seokju Cho, Heeseong Shin, Sunghwan Hong, Seungjun An, Seungjun Lee, Anurag Arnab, Paul Hongsuck Seo, and Seungryong Kim. 2023. Cat-seg: Cost aggregation for open-vocabulary semantic segmentation. arXiv preprint arXiv:2303.11797 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Sinkhorn distances: Lightspeed computation of optimal transport. Advances in Neural Information Processing Systems 26","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in Neural Information Processing Systems 26 (2013)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"e_1_3_2_1_8_1","unstructured":"M. Everingham L. Van Gool C. K. I. Williams J. Winn and A. Zisserman. [n.d.]. The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00915"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413593"},{"key":"e_1_3_2_1_12_1","volume-title":"European Conference on Computer Vision. Springer, 124--140","author":"Han Dongchen","year":"2024","unstructured":"Dongchen Han, Tianzhu Ye, Yizeng Han, Zhuofan Xia, Siyuan Pan, Pengfei Wan, Shiji Song, and Gao Huang. 2024. Agent attention: On the integration of softmax and linear attention. In European Conference on Computer Vision. Springer, 124--140."},{"key":"e_1_3_2_1_13_1","unstructured":"Kai Han Sylvestre-Alvise Rebuffi Sebastien Ehrhardt Andrea Vedaldi and Andrew Zisserman. 2020. Automatically Discovering and Learning New Visual Categories with Ranking Statistics."},{"key":"e_1_3_2_1_14_1","unstructured":"Kai Han Sylvestre-Alvise Rebuffi Sebastien Ehrhardt Andrea Vedaldi and Andrew Zisserman. 2021. AutoNovel: Automatically Discovering and Learning Novel Visual Categories. (2021)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Kai Han Andrea Vedaldi and Andrew Zisserman. 2019. Learning to Discover Novel Visual Categories via Deep Transfer Clustering.","DOI":"10.1109\/ICCV.2019.00849"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01081"},{"key":"e_1_3_2_1_17_1","unstructured":"Yen-Chang Hsu Zhaoyang Lv and Zsolt Kira. 2018. Learning to cluster in order to transfer across domains and tasks."},{"key":"e_1_3_2_1_18_1","unstructured":"Yen-Chang Hsu Zhaoyang Lv Joel Schlosser Phillip Odom and Zsolt Kira. 2019. Multi-class classification without multi-class labels."},{"key":"e_1_3_2_1_19_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_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00065"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00654"},{"key":"e_1_3_2_1_22_1","volume-title":"Language-driven semantic segmentation. arXiv preprint arXiv:2201.03546","author":"Li Boyi","year":"2022","unstructured":"Boyi Li, Kilian Q Weinberger, Serge Belongie, Vladlen Koltun, and Ren\u00e9 Ranftl. 2022. Language-driven semantic segmentation. arXiv preprint arXiv:2201.03546 (2022)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2364"},{"key":"e_1_3_2_1_24_1","first-page":"10317","article-title":"Consistent structural relation learning for zero-shot segmentation","volume":"33","author":"Li Peike","year":"2020","unstructured":"Peike Li, Yunchao Wei, and Yi Yang. 2020. Consistent structural relation learning for zero-shot segmentation. Advances in Neural Information Processing Systems 33 (2020), 10317--10327.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","volume-title":"Open-vocabulary semantic segmentation with mask-adapted clip. arXiv preprint arXiv:2210.04150","author":"Liang Feng","year":"2022","unstructured":"Feng Liang, Bichen Wu, Xiaoliang Dai, Kunpeng Li, Yinan Zhao, Hang Zhang, Peizhao Zhang, Peter Vajda, and Diana Marculescu. 2022. Open-vocabulary semantic segmentation with mask-adapted clip. arXiv preprint arXiv:2210.04150 (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00882"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.439"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00293"},{"key":"e_1_3_2_1_30_1","volume-title":"Metric learning for novelty and anomaly detection. arXiv preprint arXiv:1808.05492","author":"Masana Marc","year":"2018","unstructured":"Marc Masana, Idoia Ruiz, Joan Serrat, Joost van de Weijer, and Antonio M Lopez. 2018. Metric learning for novelty and anomaly detection. arXiv preprint arXiv:1808.05492 (2018)."},{"key":"e_1_3_2_1_31_1","volume-title":"The Role of Context for Object Detection and Semantic Segmentation in the Wild. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Mottaghi Roozbeh","year":"2014","unstructured":"Roozbeh Mottaghi, Xianjie Chen, Xiaobai Liu, Nam-Gyu Cho, Seong-Whan Lee, Sanja Fidler, Raquel Urtasun, and Alan Yuille. 2014. The Role of Context for Object Detection and Semantic Segmentation in the Wild. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00303"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 19446--19455","author":"Qin Jie","year":"2023","unstructured":"Jie Qin, Jie Wu, Pengxiang Yan, Ming Li, Ren Yuxi, Xuefeng Xiao, Yitong Wang, Rui Wang, Shilei Wen, Xin Pan, et al. 2023. FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 19446--19455."},{"key":"e_1_3_2_1_34_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_35_1","volume-title":"Boult","author":"Scheirer Walter J.","year":"2013","unstructured":"Walter J. Scheirer, Anderson Rocha, Archana Sapkota, and Terrance E. Boult. 2013. Towards Open Set Recognition. (2013)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_40"},{"key":"e_1_3_2_1_37_1","volume-title":"Conterfactual generative zero-shot semantic segmentation. arXiv preprint arXiv:2106.06360","author":"Shen Feihong","year":"2021","unstructured":"Feihong Shen, Jun Liu, and Ping Hu. 2021. Conterfactual generative zero-shot semantic segmentation. arXiv preprint arXiv:2106.06360 (2021)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02171-y"},{"key":"e_1_3_2_1_39_1","volume-title":"P-odn: Prototype-based open deep network for open set recognition. Scientific reports 10, 1","author":"Shu Yu","year":"2020","unstructured":"Yu Shu, Yemin Shi, Yaowei Wang, Tiejun Huang, and Yonghong Tian. 2020. P-odn: Prototype-based open deep network for open set recognition. Scientific reports 10, 1 (2020), 7146."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01349"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3551648"},{"key":"e_1_3_2_1_43_1","volume-title":"Hong Zhou, and Chunhua Shen.","author":"Wu Weijia","year":"2023","unstructured":"Weijia Wu, Yuzhong Zhao, Mike Zheng Shou, Hong Zhou, and Chunhua Shen. 2023. Diffumask: Synthesizing images with pixel-level annotations for semantic segmentation using diffusion models. arXiv preprint arXiv:2303.11681 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"e_1_3_2_1_45_1","volume-title":"Fahad Shahbaz Khan, and Yanwei Pang","author":"Xie Bin","year":"2023","unstructured":"Bin Xie, Jiale Cao, Jin Xie, Fahad Shahbaz Khan, and Yanwei Pang. 2023. SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation. arXiv preprint arXiv:2311.15537 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02117-4"},{"key":"e_1_3_2_1_50_1","volume-title":"Differential transformer. arXiv preprint arXiv:2410.05258","author":"Ye Tianzhu","year":"2024","unstructured":"Tianzhu Ye, Li Dong, Yuqing Xia, Yutao Sun, Yi Zhu, Gao Huang, and Furu Wei. 2024. Differential transformer. arXiv preprint arXiv:2410.05258 (2024)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01864"},{"key":"e_1_3_2_1_52_1","volume-title":"Sparse representation-based open set recognition","author":"Zhang He","year":"2016","unstructured":"He Zhang and Vishal M Patel. 2016. Sparse representation-based open set recognition. IEEE transactions on pattern analysis and machine intelligence 39, 8 (2016), 1690--1696."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.221"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01072"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00934"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"}],"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\/3746027.3754890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T03:57:07Z","timestamp":1765339027000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754890"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3754890","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754890","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"}}]}}