{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:27:07Z","timestamp":1750220827945,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61003113,61321491,61672273"],"award-info":[{"award-number":["61003113,61321491,61672273"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20171345"],"award-info":[{"award-number":["BK20171345"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350868","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"66-74","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Video Text Detection by Attentive Spatiotemporal Fusion of Deep Convolutional Features"],"prefix":"10.1145","author":[{"given":"Lan","family":"Wang","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Shi","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Su","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"volume-title":"Object Detection in Video with Spatiotemporal Sampling Networks","author":"Bertasius Gedas","key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01258-8_21"},{"volume-title":"Deformable Convolutional Networks. CoRR","year":"2017","author":"Dai Jifeng","key":"e_1_3_2_1_2_1"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Boris Epshtein Eyal Ofek and Yonatan Wexler. 2010. Detecting Text in Natural Scenes with Stroke Width Transform. In CVPR. 2963--2970.  Boris Epshtein Eyal Ofek and Yonatan Wexler. 2010. Detecting Text in Natural Scenes with Stroke Width Transform. In CVPR. 2963--2970.","DOI":"10.1109\/CVPR.2010.5540041"},{"volume-title":"Detect to Track and Track to Detect","author":"Feichtenhofer Christoph","key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.330"},{"key":"e_1_3_2_1_5_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR. 770--778.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Pan He Weilin Huang Tong He Qile Zhu Yu Qiao and Xiaolin Li. 2017. Single Shot Text Detector with Regional Attention. In ICCV. 3047--3055.  Pan He Weilin Huang Tong He Qile Zhu Yu Qiao and Xiaolin Li. 2017. Single Shot Text Detector with Regional Attention. In ICCV. 3047--3055.","DOI":"10.1109\/ICCV.2017.331"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Weilin Huang Yu Qiao and Xiaoou Tang. 2014. Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees. In ECCV. 497--511.  Weilin Huang Yu Qiao and Xiaoou Tang. 2014. Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees. In ECCV. 497--511.","DOI":"10.1007\/978-3-319-10593-2_33"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Kai Kang Wanli Ouyang Hongsheng Li and Xiaogang Wang. 2016. Object Detection from Video Tubelets with Convolutional Neural Networks. In CVPR. 817--825.  Kai Kang Wanli Ouyang Hongsheng Li and Xiaogang Wang. 2016. Object Detection from Video Tubelets with Convolutional Neural Networks. In CVPR. 817--825.","DOI":"10.1109\/CVPR.2016.95"},{"volume-title":"ICDAR 2013 Robust Reading Competition. In ICDAR. 1484--1493","author":"Karatzas Dimosthenis","key":"e_1_3_2_1_9_1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3941-x"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.06.002"},{"key":"e_1_3_2_1_12_1","volume-title":"IEEE TPAMI","volume":"25","author":"Kim Kwang In","year":"2003"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Minghui Liao Baoguang Shi Xiang Bai Xinggang Wang and Wenyu Liu. 2017. TextBoxes: A Fast Text Detector with a Single Deep Neural Network. In AAAI. 4161--4167.  Minghui Liao Baoguang Shi Xiang Bai Xinggang Wang and Wenyu Liu. 2017. TextBoxes: A Fast Text Detector with a Single Deep Neural Network. In AAAI. 4161--4167.","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Minghui Liao Zhen Zhu Baoguang Shi Gui-song Xia and Xiang Bai. 2018. Rotation-Sensitive Regression for Oriented Scene Text Detection. In CVPR. 5909--5918.  Minghui Liao Zhen Zhu Baoguang Shi Gui-song Xia and Xiang Bai. 2018. Rotation-Sensitive Regression for Oriented Scene Text Detection. In CVPR. 5909--5918.","DOI":"10.1109\/CVPR.2018.00619"},{"volume-title":"SSD: Single Shot MultiBox Detector. In ECCV. 21--37.","year":"2016","author":"Liu Wei","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2004.02.006"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Lukas Neumann and Jiri Matas. 2013. Scene Text Localization and Recognition with Oriented Stroke Detection. In ICCV. 97--104.  Lukas Neumann and Jiri Matas. 2013. Scene Text Localization and Recognition with Oriented Stroke Detection. In ICCV. 97--104.","DOI":"10.1109\/ICCV.2013.19"},{"volume-title":"Video Text Detection and Recognition: Dataset and Benchmark. In IEEE Winter Conference on Applications of Computer Vision. IEEE, 776--783","year":"2014","author":"Nguyen Phuc Xuan","key":"e_1_3_2_1_18_1"},{"key":"e_1_3_2_1_19_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster R-CNN: Towards Real-time Object Detection with Region Proposal Networks. In NIPS. 91--99.  Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster R-CNN: Towards Real-time Object Detection with Region Proposal Networks. In NIPS. 91--99."},{"key":"e_1_3_2_1_20_1","unstructured":"Baoguang Shi Xiang Bai and Serge Belongie. 2017. Detecting Oriented Text in Natural Images by Linking Segments. In CVPR. 3482--3490.  Baoguang Shi Xiang Bai and Serge Belongie. 2017. Detecting Oriented Text in Natural Images by Linking Segments. In CVPR. 3482--3490."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2010.2077772"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2198129"},{"volume-title":"Text Flow: A Unified Text Detection System in Natural Scene Images. In ICCV. 4651--4659.","year":"2015","author":"Tian Shangxuan","key":"e_1_3_2_1_23_1"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Zhi Tian Weilin Huang Tong He Pan He and Yu Qiao. 2016. Detecting Text in Natural Image with Connectionist Text Proposal Network. In ECCV. 56--72.  Zhi Tian Weilin Huang Tong He Pan He and Yu Qiao. 2016. Detecting Text in Natural Image with Connectionist Text Proposal Network. In ECCV. 56--72.","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of SPIE","volume":"8664","author":"Wang Baokang","year":"2013"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Kai Wang Boris Babenko and Serge Belongie. 2011. End-to-End Scene Text Recognition. In ICCV. 1457--1464.  Kai Wang Boris Babenko and Serge Belongie. 2011. End-to-End Scene Text Recognition. In ICCV. 1457--1464.","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Lan Wang Yang Wang Susu Shan and Feng Su. 2018. Scene Text Detection and Tracking in Video with Background Cues. In ICMR. 160--168.  Lan Wang Yang Wang Susu Shan and Feng Su. 2018. Scene Text Detection and Tracking in Video with Background Cues. In ICMR. 160--168.","DOI":"10.1145\/3206025.3206051"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2443556"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Chuhui Xue Shijian Lu and Fangneng Zhan. 2018. Accurate Scene Text Detection Through Border Semantics Awareness and Bootstrapping. In ECCV. 370--387.  Chuhui Xue Shijian Lu and Fangneng Zhan. 2018. Accurate Scene Text Detection Through Border Semantics Awareness and Bootstrapping. In ECCV. 370--387.","DOI":"10.1007\/978-3-030-01270-0_22"},{"key":"e_1_3_2_1_30_1","first-page":"7","article-title":"Tracking Based Multi-Orientation Scene Text Detection: A Unified Framework With Dynamic Programming","volume":"26","author":"Yang Chun","year":"2017","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_31_1","volume-title":"IEEE TPAMI","volume":"36","author":"Yin Xu-Cheng","year":"2014"},{"key":"e_1_3_2_1_32_1","first-page":"3","article-title":"Text From Corners: A Novel Approach to Detect Text and Caption in Videos","volume":"20","author":"Zhao Xu","year":"2011","journal-title":"IEEE TIP"},{"volume-title":"EAST: An Efficient and Accurate Scene Text Detector. In CVPR. 2642--2651.","year":"2017","author":"Zhou Xinyu","key":"e_1_3_2_1_33_1"},{"key":"e_1_3_2_1_34_1","unstructured":"Xizhou Zhu Yujie Wang Jifeng Dai Lu Yuan and Yichen Wei. 2017. Flow-Guided Feature Aggregation for Video Object Detection. In ICCV. 408--417.  Xizhou Zhu Yujie Wang Jifeng Dai Lu Yuan and Yichen Wei. 2017. Flow-Guided Feature Aggregation for Video Object Detection. In ICCV. 408--417."}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Nice France","acronym":"MM '19"},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350868","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:25Z","timestamp":1750202005000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350868"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":34,"alternative-id":["10.1145\/3343031.3350868","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350868","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}