{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:20:47Z","timestamp":1750220447541,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,3,7]],"date-time":"2021-03-07T00:00:00Z","timestamp":1615075200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872307,U1605252,62002302"],"award-info":[{"award-number":["61872307,U1605252,62002302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Fundamental Research Funds for the Central Universities","award":["20720200095"],"award-info":[{"award-number":["20720200095"]}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2020J01005"],"award-info":[{"award-number":["2020J01005"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,3,7]]},"DOI":"10.1145\/3444685.3446263","type":"proceedings-article","created":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T04:48:41Z","timestamp":1620103721000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Global and local feature alignment for video object detection"],"prefix":"10.1145","author":[{"given":"Haihui","family":"Ye","sequence":"first","affiliation":[{"name":"Xiamen Universit, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Qi","sequence":"additional","affiliation":[{"name":"Xiamen Universit, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiamen Universit, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Lu","sequence":"additional","affiliation":[{"name":"Xiamen Universit, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanzi","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiamen Universit, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,5,3]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1109\/CVPR.2018.00644"},{"key":"e_1_3_2_1_2_1","volume-title":"R-fcn: Object detection via region-based fully convolutional networks. In Advances in Neural Information Processing Systems. 379--387.","author":"Dai Jifeng","year":"2016","unstructured":"Jifeng Dai , Yi Li , Kaiming He , and 2016 . R-fcn: Object detection via region-based fully convolutional networks. In Advances in Neural Information Processing Systems. 379--387. Jifeng Dai, Yi Li, Kaiming He, and et al. 2016. R-fcn: Object detection via region-based fully convolutional networks. In Advances in Neural Information Processing Systems. 379--387."},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4660--4669","author":"Danelljan Martin","unstructured":"Martin Danelljan , Goutam Bhat , Fahad Shahbaz Khan , and et al. 2019. Atom: Accurate tracking by overlap maximization . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4660--4669 . Martin Danelljan, Goutam Bhat, Fahad Shahbaz Khan, and et al. 2019. Atom: Accurate tracking by overlap maximization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4660--4669.","key":"e_1_3_2_1_3_1"},{"volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 6678--6687","author":"Deng Hanming","unstructured":"Hanming Deng , Yang Hua , Tao Song , and et al. 2019. Object guided external memory network for video object detection . In Proceedings of the IEEE International Conference on Computer Vision. 6678--6687 . Hanming Deng, Yang Hua, Tao Song, and et al. 2019. Object guided external memory network for video object detection. In Proceedings of the IEEE International Conference on Computer Vision. 6678--6687.","key":"e_1_3_2_1_4_1"},{"volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 2758--2766","author":"Dosovitskiy Alexey","unstructured":"Alexey Dosovitskiy , Philipp Fischer , Eddy Ilg , and et al. 2015. Flownet: Learning optical flow with convolutional networks . In Proceedings of the IEEE International Conference on Computer Vision. 2758--2766 . Alexey Dosovitskiy, Philipp Fischer, Eddy Ilg, and et al. 2015. Flownet: Learning optical flow with convolutional networks. In Proceedings of the IEEE International Conference on Computer Vision. 2758--2766.","key":"e_1_3_2_1_5_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1145\/3240508.3240548"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1109\/ICCV.2015.169"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 580--587","author":"Girshick Ross","unstructured":"Ross Girshick , Jeff Donahue , Trevor Darrell , and et al. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 580--587 . Ross Girshick, Jeff Donahue, Trevor Darrell, and et al. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 580--587.","key":"e_1_3_2_1_8_1"},{"key":"e_1_3_2_1_9_1","volume-title":"Tom Le Paine, and et al","author":"Han Wei","year":"2016","unstructured":"Wei Han , Pooya Khorrami , Tom Le Paine, and et al . 2016 . Seq-nms for video object detection. arXiv preprint arXiv:1602.08465 (2016). Wei Han, Pooya Khorrami, Tom Le Paine, and et al. 2016. Seq-nms for video object detection. arXiv preprint arXiv:1602.08465 (2016)."},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3588--3597","author":"Hu Han","unstructured":"Han Hu , Jiayuan Gu , Zheng Zhang , and et al. 2018. Relation networks for object detection . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3588--3597 . Han Hu, Jiayuan Gu, Zheng Zhang, and et al. 2018. Relation networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3588--3597.","key":"e_1_3_2_1_10_1"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6409--6418","author":"Huang Zhaojin","unstructured":"Zhaojin Huang , Lichao Huang , Yongchao Gong , and et al. 2019. Mask scoring r-cnn . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6409--6418 . Zhaojin Huang, Lichao Huang, Yongchao Gong, and et al. 2019. Mask scoring r-cnn. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6409--6418.","key":"e_1_3_2_1_11_1"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2462--2470","author":"Ilg Eddy","unstructured":"Eddy Ilg , Nikolaus Mayer , Tonmoy Saikia , and et al. 2017. Flownet 2.0: Evolution of optical flow estimation with deep networks . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2462--2470 . Eddy Ilg, Nikolaus Mayer, Tonmoy Saikia, and et al. 2017. Flownet 2.0: Evolution of optical flow estimation with deep networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2462--2470.","key":"e_1_3_2_1_12_1"},{"volume-title":"Proceedings of the ACM International Conference on Multimedia. 1349--1357","author":"Ji Zhong","unstructured":"Zhong Ji , Qiankun Kong , Haoran Wang , and et al. 2019. Small and dense commodity object detection with multi-Scale receptive field attention . In Proceedings of the ACM International Conference on Multimedia. 1349--1357 . Zhong Ji, Qiankun Kong, Haoran Wang, and et al. 2019. Small and dense commodity object detection with multi-Scale receptive field attention. In Proceedings of the ACM International Conference on Multimedia. 1349--1357.","key":"e_1_3_2_1_13_1"},{"volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. 8529--8536","author":"Jiang Zhengkai","unstructured":"Zhengkai Jiang , Peng Gao , Chaoxu Guo , and et al. 2019. Video object detection with locally-weighted deformable neighbors . In Proceedings of the AAAI Conference on Artificial Intelligence. 8529--8536 . Zhengkai Jiang, Peng Gao, Chaoxu Guo, and et al. 2019. Video object detection with locally-weighted deformable neighbors. In Proceedings of the AAAI Conference on Artificial Intelligence. 8529--8536.","key":"e_1_3_2_1_14_1"},{"key":"e_1_3_2_1_15_1","first-page":"10","article-title":"2017. T-cnn: Tubelets with convolutional neural networks for object detection from videos","volume":"28","author":"Kang Kai","year":"2017","unstructured":"Kai Kang , Hongsheng Li , Junjie Yan , and . 2017. T-cnn: Tubelets with convolutional neural networks for object detection from videos . IEEE Transactions on Circuits and Systems for Video Technology 28 , 10 ( 2017 ), 2896--2907. Kai Kang, Hongsheng Li, Junjie Yan, and et al. 2017. T-cnn: Tubelets with convolutional neural networks for object detection from videos. IEEE Transactions on Circuits and Systems for Video Technology 28, 10 (2017), 2896--2907.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5197--5206","author":"Karlinsky Leonid","unstructured":"Leonid Karlinsky , Joseph Shtok , Sivan Harary , and et al. 2019. Repmet: Representative-based metric learning for classification and few-shot object detection . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5197--5206 . Leonid Karlinsky, Joseph Shtok, Sivan Harary, and et al. 2019. Repmet: Representative-based metric learning for classification and few-shot object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5197--5206.","key":"e_1_3_2_1_16_1"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5936--5944","author":"Kong Tao","unstructured":"Tao Kong , Fuchun Sun , Anbang Yao , and et al. 2017. Ron: Reverse connection with objectness prior networks for object detection . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5936--5944 . Tao Kong, Fuchun Sun, Anbang Yao, and et al. 2017. Ron: Reverse connection with objectness prior networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5936--5944.","key":"e_1_3_2_1_17_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"e_1_3_2_1_19_1","first-page":"5","article-title":"2016. Attentive contexts for object detection","volume":"19","author":"Li Jianan","year":"2016","unstructured":"Jianan Li , Yunchao Wei , Xiaodan Liang , and . 2016. Attentive contexts for object detection . IEEE Transactions on Multimedia 19 , 5 ( 2016 ), 944--954. Jianan Li, Yunchao Wei, Xiaodan Liang, and et al. 2016. Attentive contexts for object detection. IEEE Transactions on Multimedia 19, 5 (2016), 944--954.","journal-title":"IEEE Transactions on Multimedia"},{"volume-title":"Proceedings of the ACM International Conference on Multimedia. 420--428","author":"Liang Yanjie","unstructured":"Yanjie Liang , Qiangqiang Wu , Yi Liu , and et al. 2018. Robust correlation filter tracking with shepherded instance-aware proposals . In Proceedings of the ACM International Conference on Multimedia. 420--428 . Yanjie Liang, Qiangqiang Wu, Yi Liu, and et al. 2018. Robust correlation filter tracking with shepherded instance-aware proposals. In Proceedings of the ACM International Conference on Multimedia. 420--428.","key":"e_1_3_2_1_20_1"},{"volume-title":"Proceedings of the ACM Multimedia Asia. 1--6.","author":"Lin Lijian","unstructured":"Lijian Lin , Haosheng Chen , Yanjie Liang , and et al. 2019. Robust visual tracking via statistical positive sample generation and gradient aware learning . In Proceedings of the ACM Multimedia Asia. 1--6. Lijian Lin, Haosheng Chen, Yanjie Liang, and et al. 2019. Robust visual tracking via statistical positive sample generation and gradient aware learning. In Proceedings of the ACM Multimedia Asia. 1--6.","key":"e_1_3_2_1_21_1"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2117--2125","author":"Lin Tsung-Yi","unstructured":"Tsung-Yi Lin , Piotr Doll\u00e1r , Ross Girshick , and et al. 2017. Feature pyramid networks for object detection . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2117--2125 . Tsung-Yi Lin, Piotr Doll\u00e1r, Ross Girshick, and et al. 2017. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2117--2125.","key":"e_1_3_2_1_22_1"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8759--8768","author":"Liu Shu","unstructured":"Shu Liu , Lu Qi , Haifang Qin , and et al. 2018. Path aggregation network for instance segmentation . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8759--8768 . Shu Liu, Lu Qi, Haifang Qin, and et al. 2018. Path aggregation network for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8759--8768.","key":"e_1_3_2_1_23_1"},{"volume-title":"Proceedings of the European Conference on Computer Vision. 21--37","author":"Liu Wei","unstructured":"Wei Liu , Dragomir Anguelov , Dumitru Erhan , and et al. 2016. Ssd: Single shot multibox detector . In Proceedings of the European Conference on Computer Vision. 21--37 . Wei Liu, Dragomir Anguelov, Dumitru Erhan, and et al. 2016. Ssd: Single shot multibox detector. In Proceedings of the European Conference on Computer Vision. 21--37.","key":"e_1_3_2_1_24_1"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 779--788","author":"Redmon Joseph","unstructured":"Joseph Redmon , Santosh Divvala , Ross Girshick , and et al. 2016. You only look once: Unified, real-time object detection . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 779--788 . Joseph Redmon, Santosh Divvala, Ross Girshick, and et al. 2016. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 779--788.","key":"e_1_3_2_1_25_1"},{"key":"e_1_3_2_1_26_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv.1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi . 2018. Yolov3: An incremental improvement. arXiv preprint arXiv.1804.02767 ( 2018 ). Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv.1804.02767 (2018)."},{"unstructured":"Shaoqing Ren Kaiming He Ross Girshick and etal 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems. 91--99.  Shaoqing Ren Kaiming He Ross Girshick and et al. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems. 91--99.","key":"e_1_3_2_1_27_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.1007\/s11263-015-0816-y"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_29_1","DOI":"10.1109\/ICCV.2019.00985"},{"key":"e_1_3_2_1_30_1","first-page":"2","article-title":"2016. Weakly supervised learning of deformable part-based models for object detection via region proposals","volume":"19","author":"Tang Yuxing","year":"2016","unstructured":"Yuxing Tang , Xiaofang Wang , Emmanuel Dellandrea , and . 2016. Weakly supervised learning of deformable part-based models for object detection via region proposals . IEEE Transactions on Multimedia 19 , 2 ( 2016 ), 393--407. Yuxing Tang, Xiaofang Wang, Emmanuel Dellandrea, and et al. 2016. Weakly supervised learning of deformable part-based models for object detection via region proposals. IEEE Transactions on Multimedia 19, 2 (2016), 393--407.","journal-title":"IEEE Transactions on Multimedia"},{"unstructured":"Ashish Vaswani Noam Shazeer Nikiand Parmar and etal 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008.  Ashish Vaswani Noam Shazeer Nikiand Parmar and et al. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008.","key":"e_1_3_2_1_31_1"},{"volume-title":"Proceedings of the European Conference on Computer Vision. 542--557","author":"Wang Shiyao","unstructured":"Shiyao Wang , Yucong Zhou , Junjie Yan , and et al. 2018. Fully motion-aware network for video object detection . In Proceedings of the European Conference on Computer Vision. 542--557 . Shiyao Wang, Yucong Zhou, Junjie Yan, and et al. 2018. Fully motion-aware network for video object detection. In Proceedings of the European Conference on Computer Vision. 542--557.","key":"e_1_3_2_1_32_1"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7794--7803","author":"Wang Xiaolong","unstructured":"Xiaolong Wang , Ross Girshick , Abhinav Gupta , and et al. 2018. Non-local neural networks . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7794--7803 . Xiaolong Wang, Ross Girshick, Abhinav Gupta, and et al. 2018. Non-local neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7794--7803.","key":"e_1_3_2_1_33_1"},{"volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 9217--9225","author":"Wu Haiping","unstructured":"Haiping Wu , Yuntao Chen , Naiyan Wang , and et al. 2019. Sequence level semantics aggregation for video object detection . In Proceedings of the IEEE International Conference on Computer Vision. 9217--9225 . Haiping Wu, Yuntao Chen, Naiyan Wang, and et al. 2019. Sequence level semantics aggregation for video object detection. In Proceedings of the IEEE International Conference on Computer Vision. 9217--9225.","key":"e_1_3_2_1_34_1"},{"volume-title":"Proceedings of the ACM international conference on Multimedia. 516--520","author":"Yu Jiahui","unstructured":"Jiahui Yu , Yuning Jiang , Zhangyang Wang , and et al. 2016. Unitbox: An advanced object detection network . In Proceedings of the ACM international conference on Multimedia. 516--520 . Jiahui Yu, Yuning Jiang, Zhangyang Wang, and et al. 2016. Unitbox: An advanced object detection network. In Proceedings of the ACM international conference on Multimedia. 516--520.","key":"e_1_3_2_1_35_1"},{"volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 408--417","author":"Zhu Xizhou","unstructured":"Xizhou Zhu , Yujie Wang , Jifeng Dai , and et al. 2017. Flow-guided feature aggregation for video object detection . In Proceedings of the IEEE International Conference on Computer Vision. 408--417 . Xizhou Zhu, Yujie Wang, Jifeng Dai, and et al. 2017. Flow-guided feature aggregation for video object detection. In Proceedings of the IEEE International Conference on Computer Vision. 408--417.","key":"e_1_3_2_1_36_1"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2349--2358","author":"Zhu Xizhou","unstructured":"Xizhou Zhu , Yuwen Xiong , Jifeng Dai , and et al. 2017. Deep feature flow for video recognition . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2349--2358 . Xizhou Zhu, Yuwen Xiong, Jifeng Dai, and et al. 2017. Deep feature flow for video recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2349--2358.","key":"e_1_3_2_1_37_1"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MMAsia '20","name":"MMAsia '20: ACM Multimedia Asia","location":"Virtual Event Singapore"},"container-title":["Proceedings of the 2nd ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3444685.3446263","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3444685.3446263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:46Z","timestamp":1750193266000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3444685.3446263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,7]]},"references-count":37,"alternative-id":["10.1145\/3444685.3446263","10.1145\/3444685"],"URL":"https:\/\/doi.org\/10.1145\/3444685.3446263","relation":{},"subject":[],"published":{"date-parts":[[2021,3,7]]},"assertion":[{"value":"2021-05-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}