{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:21:36Z","timestamp":1755926496041,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2018AAA0102003"],"award-info":[{"award-number":["2018AAA0102003"]}]},{"name":"Key Research Program of Frontier Sciences CAS","award":["QYZDJ-SSW-SYS013"],"award-info":[{"award-number":["QYZDJ-SSW-SYS013"]}]},{"name":"National Nat- ural Science Foundation of China","award":["61620106009 U1636214 61931008 61836002 61672514 61976202"],"award-info":[{"award-number":["61620106009 U1636214 61931008 61836002 61672514 61976202"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3414035","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:26:53Z","timestamp":1602505613000},"page":"2048-2056","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["DMVOS"],"prefix":"10.1145","author":[{"given":"Peisong","family":"Wen","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Ruolin","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications & SenseTime, Beijing, China"}]},{"given":"Qianqian","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Chen","family":"Qian","sequence":"additional","affiliation":[{"name":"SenseTime, Beijing, China"}]},{"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing; Shenzhen, China"}]},{"given":"Runmin","family":"Cong","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}]},{"given":"Jianlou","family":"Si","sequence":"additional","affiliation":[{"name":"SenseTime, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_2_1_1","DOI":"10.1109\/CVPR.2018.00626"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_2_1","DOI":"10.1109\/CVPR.2018.00464"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_3_1","DOI":"10.1007\/978-3-319-48881-3_56"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_4_1","DOI":"10.1109\/CVPR.2017.565"},{"key":"e_1_3_2_2_5_1","volume-title":"Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams. In IEEE International Conference on Computer Vision. 3415--3424","author":"Chai Yuning","year":"2019","unstructured":"Yuning Chai . 2019 . Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams. In IEEE International Conference on Computer Vision. 3415--3424 . Yuning Chai. 2019. Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams. In IEEE International Conference on Computer Vision. 3415--3424."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_6_1","DOI":"10.1109\/CVPR.2018.00130"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_7_1","DOI":"10.1109\/CVPR.2018.00774"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_8_1","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"e_1_3_2_2_9_1","volume-title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing. In IEEE International Conference on Computer Vision. 8480--8489","author":"Duarte Kevin","year":"2019","unstructured":"Kevin Duarte , Yogesh S Rawat , and Mubarak Shah . 2019 . CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing. In IEEE International Conference on Computer Vision. 8480--8489 . Kevin Duarte, Yogesh S Rawat, and Mubarak Shah. 2019. CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing. In IEEE International Conference on Computer Vision. 8480--8489."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_10_1","DOI":"10.1007\/978-3-030-01267-0_12"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_11_1","DOI":"10.1109\/CVPR.2018.00152"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_12_1","DOI":"10.1007\/978-3-030-01237-3_4"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_13_1","DOI":"10.1109\/CVPR.2017.336"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_14_1","DOI":"10.1109\/CVPR.2017.790"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_15_1","DOI":"10.1109\/CVPR.2019.00916"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_16_1","DOI":"10.1007\/s11263-019-01164-6"},{"key":"e_1_3_2_2_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_18_1","DOI":"10.1109\/CVPR.2017.34"},{"key":"e_1_3_2_2_19_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition. 5455--5463","author":"Li Guanbin","year":"2015","unstructured":"Guanbin Li and Yizhou Yu . 2015 . Visual saliency based on multiscale deep features . In IEEE Conference on Computer Vision and Pattern Recognition. 5455--5463 . Guanbin Li and Yizhou Yu. 2015. Visual saliency based on multiscale deep features. In IEEE Conference on Computer Vision and Pattern Recognition. 5455--5463."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_20_1","DOI":"10.1007\/978-3-030-01219-9_6"},{"key":"e_1_3_2_2_21_1","volume-title":"AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation. In IEEE International Conference on Computer Vision. 3949--3957","author":"Lin Huaijia","year":"2019","unstructured":"Huaijia Lin , Xiaojuan Qi , and Jiaya Jia . 2019 . AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation. In IEEE International Conference on Computer Vision. 3949--3957 . Huaijia Lin, Xiaojuan Qi, and Jiaya Jia. 2019. AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation. In IEEE International Conference on Computer Vision. 3949--3957."},{"key":"e_1_3_2_2_22_1","volume-title":"Multi-Scale Triplet CNN for Person Re-Identification. In ACM international conference on Multimedia. 192--196","author":"Liu Jiawei","year":"2016","unstructured":"Jiawei Liu , Zheng jun Zha , Qi Tian , Dong Liu , Ting Yao , Qiang Ling , and Tao Mei . 2016 . Multi-Scale Triplet CNN for Person Re-Identification. In ACM international conference on Multimedia. 192--196 . Jiawei Liu, Zheng jun Zha, Qi Tian, Dong Liu, Ting Yao, Qiang Ling, and Tao Mei. 2016. Multi-Scale Triplet CNN for Person Re-Identification. In ACM international conference on Multimedia. 192--196."},{"key":"e_1_3_2_2_23_1","volume-title":"Asian Conference on Computer Vision. Springer, 565--580","author":"Luiten Jonathon","year":"2018","unstructured":"Jonathon Luiten , Paul Voigtlaender , and Bastian Leibe . 2018 . PReMVOS: Proposal-generation, refinement and merging for video object segmentation . In Asian Conference on Computer Vision. Springer, 565--580 . Jonathon Luiten, Paul Voigtlaender, and Bastian Leibe. 2018. PReMVOS: Proposal-generation, refinement and merging for video object segmentation. In Asian Conference on Computer Vision. Springer, 565--580."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_24_1","DOI":"10.1109\/TPAMI.2018.2838670"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_25_1","DOI":"10.1109\/CVPR.2019.00904"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_26_1","DOI":"10.1109\/ICCV.2019.00932"},{"key":"e_1_3_2_2_27_1","volume-title":"Learning Video Object Segmentation From Static Images. In The IEEE Conference on Computer Vision and Pattern Recognition.","author":"Perazzi Federico","year":"2017","unstructured":"Federico Perazzi , Anna Khoreva , Rodrigo Benenson , Bernt Schiele , and Alexander Sorkine-Hornung . 2017 . Learning Video Object Segmentation From Static Images. In The IEEE Conference on Computer Vision and Pattern Recognition. Federico Perazzi, Anna Khoreva, Rodrigo Benenson, Bernt Schiele, and Alexander Sorkine-Hornung. 2017. Learning Video Object Segmentation From Static Images. In The IEEE Conference on Computer Vision and Pattern Recognition."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_28_1","DOI":"10.1109\/CVPR.2016.85"},{"key":"e_1_3_2_2_29_1","volume-title":"The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675","author":"Pont-Tuset Jordi","year":"2017","unstructured":"Jordi Pont-Tuset , Federico Perazzi , Sergi Caelles , Pablo Arbel\u00e1ez , Alex Sorkine-Hornung , and Luc Van Gool . 2017. The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675 ( 2017 ). Jordi Pont-Tuset, Federico Perazzi, Sergi Caelles, Pablo Arbel\u00e1ez, Alex Sorkine-Hornung, and Luc Van Gool. 2017. The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_30_1","DOI":"10.1109\/ICCV.2017.238"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_31_1","DOI":"10.1109\/CVPR.2019.00971"},{"key":"e_1_3_2_2_32_1","volume-title":"The 2017 DAVIS Challenge on Video Object Segmentation-CVPR Workshops","volume":"5","author":"Voigtlaender Paul","year":"2017","unstructured":"Paul Voigtlaender and Bastian Leibe . 2017 . Online adaptation of convolutional neural networks for the 2017 davis challenge on video object segmentation . In The 2017 DAVIS Challenge on Video Object Segmentation-CVPR Workshops , Vol. 5 . Paul Voigtlaender and Bastian Leibe. 2017. Online adaptation of convolutional neural networks for the 2017 davis challenge on video object segmentation. In The 2017 DAVIS Challenge on Video Object Segmentation-CVPR Workshops, Vol. 5."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_33_1","DOI":"10.1109\/CVPR.2019.00142"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_34_1","DOI":"10.1109\/CVPR.2018.00813"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_35_1","DOI":"10.1109\/ICCV.2019.00408"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_36_1","DOI":"10.1109\/CVPR.2018.00770"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_37_1","DOI":"10.1109\/CVPR.2018.00125"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_38_1","DOI":"10.1109\/CVPR.2019.00147"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_39_1","DOI":"10.1109\/CVPR.2013.153"},{"key":"e_1_3_2_2_40_1","volume-title":"Robust Deep Co-Saliency Detection With Group Semantic and Pyramid Attention","author":"Zha Zheng-Jun","year":"2020","unstructured":"Zheng-Jun Zha , Chong Wang , Dong Liu , Hongtao Xie , and Yongdong Zhang . 2020. Robust Deep Co-Saliency Detection With Group Semantic and Pyramid Attention . IEEE Transactions on Neural Networks and Learning Systems ( 2020 ), 1--11. Zheng-Jun Zha, Chong Wang, Dong Liu, Hongtao Xie, and Yongdong Zhang. 2020. Robust Deep Co-Saliency Detection With Group Semantic and Pyramid Attention. IEEE Transactions on Neural Networks and Learning Systems (2020), 1--11."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_41_1","DOI":"10.1109\/ICCV.2019.00568"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '20","name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA"},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3414035","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3414035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:23Z","timestamp":1750197683000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3414035"}},"subtitle":["Discriminative Matching for Real-time Video Object Segmentation"],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":41,"alternative-id":["10.1145\/3394171.3414035","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3414035","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}