{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T23:12:08Z","timestamp":1772752328580,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548227","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"2969-2977","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Dynamic Transformer for Few-shot Instance Segmentation"],"prefix":"10.1145","author":[{"given":"Haochen","family":"Wang","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"given":"Yongtuo","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"given":"Subhransu","family":"Maji","sequence":"additional","affiliation":[{"name":"University of Massachusetts, Amherst, Netherlands"}]},{"given":"Jan-Jakob","family":"Sonke","sequence":"additional","affiliation":[{"name":"The Netherlands Cancer Institute, Amsterdam, Netherlands"}]},{"given":"Efstratios","family":"Gavves","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_2_3_1","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen , George Papandreou , Iasonas Kokkinos , Kevin Murphy , and Alan L Yuille . 2017 . Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs . IEEE transactions on pattern analysis and machine intelligence 40, 4 (2017), 834--848. Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence 40, 4 (2017), 834--848."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"e_1_3_2_2_5_1","volume-title":"Masked-attention mask transformer for universal image segmentation. arXiv preprint arXiv:2112.01527","author":"Cheng Bowen","year":"2021","unstructured":"Bowen Cheng , Ishan Misra , Alexander G Schwing , Alexander Kirillov , and Rohit Girdhar . 2021. Masked-attention mask transformer for universal image segmentation. arXiv preprint arXiv:2112.01527 ( 2021 ). Bowen Cheng, Ishan Misra, Alexander G Schwing, Alexander Kirillov, and Rohit Girdhar. 2021. Masked-attention mask transformer for universal image segmentation. arXiv preprint arXiv:2112.01527 (2021)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00919"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00124"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_9"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_2_14_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Fixing weight decay regularization in adam. (2018).  Ilya Loshchilov and Frank Hutter. 2018. Fixing weight decay regularization in adam. (2018)."},{"key":"e_1_3_2_2_15_1","volume-title":"Trackformer: Multi-object tracking with transformers. arXiv preprint arXiv:2101.02702","author":"Meinhardt Tim","year":"2021","unstructured":"Tim Meinhardt , Alexander Kirillov , Laura Leal-Taixe , and Christoph Feichtenhofer . 2021 . Trackformer: Multi-object tracking with transformers. arXiv preprint arXiv:2101.02702 (2021). Tim Meinhardt, Alexander Kirillov, Laura Leal-Taixe, and Christoph Feichtenhofer. 2021. Trackformer: Multi-object tracking with transformers. arXiv preprint arXiv:2101.02702 (2021)."},{"key":"e_1_3_2_2_16_1","volume-title":"One-shot instance segmentation. arXiv preprint arXiv:1811.11507","author":"Michaelis Claudio","year":"2018","unstructured":"Claudio Michaelis , Ivan Ustyuzhaninov , Matthias Bethge , and Alexander S Ecker . 2018. One-shot instance segmentation. arXiv preprint arXiv:1811.11507 ( 2018 ). Claudio Michaelis, Ivan Ustyuzhaninov, Matthias Bethge, and Alexander S Ecker. 2018. One-shot instance segmentation. arXiv preprint arXiv:1811.11507 (2018)."},{"key":"e_1_3_2_2_17_1","volume-title":"V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV)","author":"Milletari Fausto","year":"2016","unstructured":"Fausto Milletari , Nassir Navab , and Seyed-Ahmad Ahmadi . 2016 . V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV) . IEEE , 565--571. Fausto Milletari, Nassir Navab, and Seyed-Ahmad Ahmadi. 2016. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV). IEEE, 565--571."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01095"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_2_20_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","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 28 ( 2015 ). 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 28 (2015)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013717"},{"key":"e_1_3_2_2_23_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017. Attention is all you need. Advances in neural information processing systems 30 ( 2017 ). Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_43"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Jingdong Wang Ke Sun Tianheng Cheng Borui Jiang Chaorui Deng Yang Zhao Dong Liu Yadong Mu Mingkui Tan Xinggang Wang etal 2020. Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence 43 10 (2020) 3349--3364.  Jingdong Wang Ke Sun Tianheng Cheng Borui Jiang Chaorui Deng Yang Zhao Dong Liu Yadong Mu Mingkui Tan Xinggang Wang et al. 2020. Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence 43 10 (2020) 3349--3364.","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 568--578","author":"Xie Enze","year":"2021","unstructured":"WenhaiWang, Enze Xie , Xiang Li , Deng-Ping Fan , Kaitao Song , Ding Liang , Tong Lu , Ping Luo , and Ling Shao . 2021 . Pyramid vision transformer: A versatile backbone for dense prediction without convolutions . In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 568--578 . WenhaiWang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. 2021. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 568--578."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"e_1_3_2_2_28_1","volume-title":"Seqformer: a frustratingly simple model for video instance segmentation. arXiv preprint arXiv:2112.08275","author":"Jiang Yi","year":"2021","unstructured":"JunfengWu, Yi Jiang , Wenqing Zhang , Xiang Bai , and Song Bai . 2021. Seqformer: a frustratingly simple model for video instance segmentation. arXiv preprint arXiv:2112.08275 ( 2021 ). JunfengWu, Yi Jiang,Wenqing Zhang, Xiang Bai, and Song Bai. 2021. Seqformer: a frustratingly simple model for video instance segmentation. arXiv preprint arXiv:2112.08275 (2021)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00967"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00860"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00968"},{"key":"e_1_3_2_2_32_1","volume-title":"Few-shot segmentation via cycle-consistent transformer. Advances in Neural Information Processing Systems 34","author":"Zhang Gengwei","year":"2021","unstructured":"Gengwei Zhang , Guoliang Kang , Yi Yang , and Yunchao Wei . 2021. Few-shot segmentation via cycle-consistent transformer. Advances in Neural Information Processing Systems 34 ( 2021 ). Gengwei Zhang, Guoliang Kang, Yi Yang, and Yunchao Wei. 2021. Few-shot segmentation via cycle-consistent transformer. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00093"},{"key":"e_1_3_2_2_34_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu , Weijie Su , Lewei Lu , Bin Li , Xiaogang Wang , and Jifeng Dai . 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 ( 2020 ). Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548227","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:20Z","timestamp":1750186820000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":34,"alternative-id":["10.1145\/3503161.3548227","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548227","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}