{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T04:58:25Z","timestamp":1755838705618,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,6,5]],"date-time":"2018-06-05T00:00:00Z","timestamp":1528156800000},"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":[[2018,6,5]]},"DOI":"10.1145\/3206025.3206052","type":"proceedings-article","created":{"date-parts":[[2018,6,11]],"date-time":"2018-06-11T12:36:20Z","timestamp":1528720580000},"page":"362-369","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Multi-Scale Spatiotemporal Conv-LSTM Network for Video Saliency Detection"],"prefix":"10.1145","author":[{"given":"Yi","family":"Tang","sequence":"first","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbin","family":"Zou","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Jin","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xia","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,6,5]]},"reference":[{"volume-title":"Object segmentation by long term analysis of point trajectories Proceedings of the European Conference on Computer Vision","author":"Brox Thomas","key":"e_1_3_2_1_1_1","unstructured":"Thomas Brox and Jitendra Malik . 2010. Object segmentation by long term analysis of point trajectories Proceedings of the European Conference on Computer Vision . Springer , 282--295. Thomas Brox and Jitendra Malik. 2010. Object segmentation by long term analysis of point trajectories Proceedings of the European Conference on Computer Vision. Springer, 282--295."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2670143"},{"key":"e_1_3_2_1_3_1","volume-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint:1412.7062","author":"Chen Liang-Chieh","year":"2014","unstructured":"Liang-Chieh Chen , George Papandreou , Iasonas Kokkinos , Kevin Murphy , and Alan L Yuille . 2014. Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint:1412.7062 ( 2014 ). Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2014. Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint:1412.7062 (2014)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"e_1_3_2_1_5_1","volume-title":"Kai Li, and Fei Fei Li.","author":"Deng Jia","year":"2009","unstructured":"Jia Deng , Wei Dong , Richard Socher , Li Jia Li , Kai Li, and Fei Fei Li. 2009 . ImageNet: A large-scale hierarchical image database Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 248--255. Jia Deng, Wei Dong, Richard Socher, Li Jia Li, Kai Li, and Fei Fei Li. 2009. ImageNet: A large-scale hierarchical image database Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 248--255."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3078988"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2260166"},{"key":"e_1_3_2_1_9_1","unstructured":"Dashan Gao Vijay Mahadevan and Nuno Vasconcelos. 2008. The discriminant center-surround hypothesis for bottom-up saliency Proceedings of the Advances in Neural Information Processing Systems. 497--504.   Dashan Gao Vijay Mahadevan and Nuno Vasconcelos. 2008. The discriminant center-surround hypothesis for bottom-up saliency Proceedings of the Advances in Neural Information Processing Systems. 497--504."},{"volume-title":"Deeply supervised salient object detection with short connections Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Hou Qibin","key":"e_1_3_2_1_10_1","unstructured":"Qibin Hou , Ming-Ming Cheng , Xiaowei Hu , Zhuowen Tu , and A Borji . 2017. Deeply supervised salient object detection with short connections Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . IEEE. Qibin Hou, Ming-Ming Cheng, Xiaowei Hu, Zhuowen Tu, and A Borji. 2017. Deeply supervised salient object detection with short connections Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.271"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2425544"},{"key":"e_1_3_2_1_13_1","volume-title":"Adam: A Method for Stochastic Optimization. Computer Science","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A Method for Stochastic Optimization. Computer Science (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. Computer Science (2014)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.273"},{"volume-title":"2016 a. Deep contrast learning for salient object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Li Guanbin","key":"e_1_3_2_1_15_1","unstructured":"Guanbin Li and Yizhou Yu . 2016 a. Deep contrast learning for salient object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 478--487. Guanbin Li and Yizhou Yu. 2016 a. Deep contrast learning for salient object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 478--487."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2602079"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2579306"},{"key":"e_1_3_2_1_18_1","volume-title":"Dhsnet: Deep hierarchical saliency network for salient object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 678--686.","author":"Liu Nian","year":"2016","unstructured":"Nian Liu and Junwei Han . 2016 . Dhsnet: Deep hierarchical saliency network for salient object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 678--686. Nian Liu and Junwei Han. 2016. Dhsnet: Deep hierarchical saliency network for salient object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 678--686."},{"key":"e_1_3_2_1_19_1","volume-title":"Learning Efficient Spatial-Temporal Gait Features with Deep Learning for Human Identification. Neuroinformatics","author":"Liu Wu","year":"2018","unstructured":"Wu Liu , Cheng Zhang , Huadong Ma , and Shuangqun Li. 2018. Learning Efficient Spatial-Temporal Gait Features with Deep Learning for Human Identification. Neuroinformatics ( 2018 ), 1--15. Wu Liu, Cheng Zhang, Huadong Ma, and Shuangqun Li. 2018. Learning Efficient Spatial-Temporal Gait Features with Deep Learning for Human Identification. Neuroinformatics (2018), 1--15."},{"volume-title":"Fully convolutional networks for semantic segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Long Jonathan","key":"e_1_3_2_1_20_1","unstructured":"Jonathan Long , Evan Shelhamer , and Trevor Darrell . 2015. Fully convolutional networks for semantic segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 3431--3440. Jonathan Long, Evan Shelhamer, and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3431--3440."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.223"},{"key":"e_1_3_2_1_22_1","volume-title":"Two-stream Collaborative Learning with Spatial-Temporal Attention for Video Classification. arXiv preprint arXiv:1711.03273","author":"Peng Yuxin","year":"2017","unstructured":"Yuxin Peng , Yunzhen Zhao , and Junchao Zhang . 2017. Two-stream Collaborative Learning with Spatial-Temporal Attention for Video Classification. arXiv preprint arXiv:1711.03273 ( 2017 ). Yuxin Peng, Yunzhen Zhao, and Junchao Zhang. 2017. Two-stream Collaborative Learning with Spatial-Temporal Attention for Video Classification. arXiv preprint arXiv:1711.03273 (2017)."},{"volume-title":"Saliency filters: Contrast based filtering for salient region detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Perazzi Federico","key":"e_1_3_2_1_23_1","unstructured":"Federico Perazzi , Philipp Kr\u00e4henb\u00fchl , Yael Pritch , and Alexander Hornung . 2012. Saliency filters: Contrast based filtering for salient region detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 733--740. Federico Perazzi, Philipp Kr\u00e4henb\u00fchl, Yael Pritch, and Alexander Hornung . 2012. Saliency filters: Contrast based filtering for salient region detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 733--740."},{"key":"e_1_3_2_1_24_1","volume-title":"Markus Gross, and Alexander Sorkine-Hornung.","author":"Perazzi Federico","year":"2016","unstructured":"Federico Perazzi , Jordi Pont-Tuset , Brian McWilliams , Luc Van Gool , Markus Gross, and Alexander Sorkine-Hornung. 2016 . A benchmark dataset and evaluation methodology for video object segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE , 724--732. Federico Perazzi, Jordi Pont-Tuset, Brian McWilliams, Luc Van Gool, Markus Gross, and Alexander Sorkine-Hornung. 2016. A benchmark dataset and evaluation methodology for video object segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 724--732."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888150.1888180"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1167\/9.12.15"},{"volume-title":"2015 a. Deep networks for saliency detection via local estimation and global search Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Wang Lijun","key":"e_1_3_2_1_27_1","unstructured":"Lijun Wang , Huchuan Lu , Xiang Ruan , and Ming-Hsuan Yang . 2015 a. Deep networks for saliency detection via local estimation and global search Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 3183--3192. Lijun Wang, Huchuan Lu, Xiang Ruan, and Ming-Hsuan Yang. 2015 a. Deep networks for saliency detection via local estimation and global search Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3183--3192."},{"volume-title":"Saliency detection with recurrent fully convolutional networks Proceedings of the European Conference on Computer Vision","author":"Wang Linzhao","key":"e_1_3_2_1_28_1","unstructured":"Linzhao Wang , Lijun Wang , Huchuan Lu , Pingping Zhang , and Xiang Ruan . 2016. Saliency detection with recurrent fully convolutional networks Proceedings of the European Conference on Computer Vision . Springer , 825--841. Linzhao Wang, Lijun Wang, Huchuan Lu, Pingping Zhang, and Xiang Ruan. 2016. Saliency detection with recurrent fully convolutional networks Proceedings of the European Conference on Computer Vision. Springer, 825--841."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298961"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2460013"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754941"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_3"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3078989"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180824"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298731"},{"volume-title":"Saliency-guided video classification via adaptively weighted learning Proceedings of the IEEE International Conference on Multimedia and Expo","author":"Zhao Yunzhen","key":"e_1_3_2_1_36_1","unstructured":"Yunzhen Zhao and Yuxin Peng . 2017. Saliency-guided video classification via adaptively weighted learning Proceedings of the IEEE International Conference on Multimedia and Expo . IEEE , 847--852. Yunzhen Zhao and Yuxin Peng. 2017. Saliency-guided video classification via adaptively weighted learning Proceedings of the IEEE International Conference on Multimedia and Expo. IEEE, 847--852."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.429"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.54"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Wenbin Zou Kidiyo Kpalma Zhi Liu and Joseph Ronsin. 2013. Segmentation driven low-rank matrix recovery for saliency detection Proceedings of the British Machine Vision on Conference. 1--13.  Wenbin Zou Kidiyo Kpalma Zhi Liu and Joseph Ronsin. 2013. Segmentation driven low-rank matrix recovery for saliency detection Proceedings of the British Machine Vision on Conference. 1--13.","DOI":"10.5244\/C.27.78"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2456497"}],"event":{"name":"ICMR '18: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Yokohama Japan","acronym":"ICMR '18"},"container-title":["Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3206025.3206052","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3206025.3206052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:15Z","timestamp":1750208895000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3206025.3206052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,5]]},"references-count":40,"alternative-id":["10.1145\/3206025.3206052","10.1145\/3206025"],"URL":"https:\/\/doi.org\/10.1145\/3206025.3206052","relation":{},"subject":[],"published":{"date-parts":[[2018,6,5]]},"assertion":[{"value":"2018-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}