{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T07:13:44Z","timestamp":1763968424626,"version":"3.37.3"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T00:00:00Z","timestamp":1605225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T00:00:00Z","timestamp":1605225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s10489-020-01961-4","type":"journal-article","created":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T06:02:53Z","timestamp":1605247373000},"page":"3450-3459","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["STA-Net: spatial-temporal attention network for video salient object detection"],"prefix":"10.1007","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2442-330X","authenticated-orcid":false,"given":"Hong-Bo","family":"Bi","sequence":"first","affiliation":[]},{"given":"Di","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Hui-Hui","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Li-Na","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Hua-Ping","family":"Guan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,13]]},"reference":[{"key":"1961_CR1","doi-asserted-by":"crossref","unstructured":"Fukuchi K, Miyazato K, Kimura A, Takagi S, Yamato J (2009) Saliency-based video segmentation with graph cuts and sequentially updated priors. In: 2009 IEEE International Conference on Multimedia and Expo, IEEE, pp 638\u2013641","DOI":"10.1109\/ICME.2009.5202577"},{"key":"1961_CR2","doi-asserted-by":"crossref","unstructured":"Hua G, Zhang C, Liu Z, Zhang Z, Shan Y (2009) Efficient scale-space spatiotemporal saliency tracking for distortion-free video retargeting. In: Asian Conference on Computer Vision, Springer, Berlin, Heidelberg, pp 182\u2013192","DOI":"10.1007\/978-3-642-12304-7_18"},{"key":"1961_CR3","doi-asserted-by":"crossref","unstructured":"Chen Y, Zhang W, Wang S, Li L, Huang Q (2018) Saliency-based spatiotemporal attention for video captioning. In: 2018 IEEE Fourth International Conference on Multimedia Big Data BigMM pp. 1\u20138, IEEE","DOI":"10.1109\/BigMM.2018.8499257"},{"issue":"1","key":"1961_CR4","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1109\/TIP.2013.2282897","volume":"23","author":"H Hadizadeh","year":"2013","unstructured":"Hadizadeh H, Baji\u0107 I. V. (2013) Saliency-aware video compression. IEEE Trans Image Process 23(1):19\u201333","journal-title":"IEEE Trans Image Process"},{"key":"1961_CR5","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/j.patcog.2017.07.028","volume":"72","author":"Z Tu","year":"2017","unstructured":"Tu Z, Guo Z, Xie W, Yan M, Veltkamp RC, Li B, Yuan J (2017) Fusing disparate object signatures for salient object detection in video. Pattern Recogn 72:285\u2013299","journal-title":"Pattern Recogn"},{"issue":"9","key":"1961_CR6","doi-asserted-by":"publisher","first-page":"10685","DOI":"10.1007\/s11042-017-4822-7","volume":"77","author":"L Huang","year":"2018","unstructured":"Huang L, Luo B (2018) Video-based salient object detection via spatio-temporal difference and coherence. Multimedia Tools and Applications 77(9):10685\u201310699","journal-title":"Multimedia Tools and Applications"},{"key":"1961_CR7","doi-asserted-by":"crossref","unstructured":"Fu K, Gu IY, Yun Y, Gong C, Yang J (2014) Graph construction for salient object detection in videos. In: 2014 22nd International Conference on Pattern Recognition (pp. 2371\u20132376), IEEE","DOI":"10.1109\/ICPR.2014.411"},{"key":"1961_CR8","doi-asserted-by":"crossref","unstructured":"Wei Y, Wen F, Zhu W, Sun J (2012) Geodesic saliency using background priors. In: European conference on computer vision (pp. 29\u201342). Springer, Berlin, Heidelberg","DOI":"10.1007\/978-3-642-33712-3_3"},{"issue":"7","key":"1961_CR9","doi-asserted-by":"publisher","first-page":"3345","DOI":"10.1109\/TIP.2018.2813165","volume":"27","author":"Y Chen","year":"2018","unstructured":"Chen Y, Zou W, Tang Y, Li X, Xu C, Komodakis N (2018) SCOM: Spatiotemporal Constrained optimization for salient object detection. IEEE Trans Image Process 27(7):3345\u20133357","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"1961_CR10","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/0010-0285(80)90005-5","volume":"12","author":"AM Treisman","year":"1980","unstructured":"Treisman AM, Gelade G (1980) A feature-integration theory of attention. Cognitive psychology 12(1):97\u2013136","journal-title":"Cognitive psychology"},{"issue":"7","key":"1961_CR11","doi-asserted-by":"publisher","first-page":"3425","DOI":"10.1109\/TIP.2016.2631900","volume":"26","author":"T Xi","year":"2016","unstructured":"Xi T, Zhao W, Wang H, Lin W (2016) Salient object detection with spatiotemporal background priors for video. IEEE Trans Image Process 26(7):3425\u20133436","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"1961_CR12","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/TPAMI.2017.2662005","volume":"40","author":"W Wang","year":"2017","unstructured":"Wang W, Shen J, Yang R, Porikli F (2017) Saliency-aware video object segmentation. IEEE transactions on pattern analysis and machine intelligence 40(1):20\u201333","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"11","key":"1961_CR13","doi-asserted-by":"publisher","first-page":"4185","DOI":"10.1109\/TIP.2015.2460013","volume":"24","author":"W Wang","year":"2015","unstructured":"Wang W, Shen J, Shao L (2015) Consistent video saliency using local gradient flow optimization and global refinement. IEEE Trans Image Process 24(11):4185\u20134196","journal-title":"IEEE Trans Image Process"},{"key":"1961_CR14","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv:1409.0473"},{"key":"1961_CR15","doi-asserted-by":"crossref","unstructured":"Nie G, Guo Y, Liu Y, Wang Y (2017) Real-time salient object detection based on fully convolutional networks. In: Chinese Conference on Image and Graphics Technologies (pp. 189\u2013198). Springer, Singapore","DOI":"10.1007\/978-981-10-7389-2_19"},{"key":"1961_CR16","doi-asserted-by":"crossref","unstructured":"Bi H, Lu D, Li N, Yang L, Guan H (2019) Multi-Level Model for Video Saliency Detection. In: 2019 IEEE International Conference on Image Processing (ICIP) (pp. 4654\u20134658), IEEE","DOI":"10.1109\/ICIP.2019.8803611"},{"key":"1961_CR17","doi-asserted-by":"crossref","unstructured":"Fan DP, Wang W, Cheng MM, Shen J (2019) Shifting more attention to video salient object detection. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp 8554\u20138564","DOI":"10.1109\/CVPR.2019.00875"},{"key":"1961_CR18","doi-asserted-by":"crossref","unstructured":"Song H, Wang W, Zhao S, Shen J, Lam KM (2018) Pyramid dilated deeper convlstm for video salient object detection. In: proceedings of the European conference on computer vision (ECCV) (pp. 715\u2013731)","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"1961_CR19","doi-asserted-by":"crossref","unstructured":"Li G, Xie Y, Wei T, Wang K, Lin L (2018) Flow guided recurrent neural encoder for video salient object detection. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp 3243\u20133252","DOI":"10.1109\/CVPR.2018.00342"},{"key":"1961_CR20","doi-asserted-by":"crossref","unstructured":"Wang F, Jiang M, Qian C, Yang S, Li C, Zhang H, Tang X (2017) Residual attention network for image classification. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp 3156\u20133164","DOI":"10.1109\/CVPR.2017.683"},{"key":"1961_CR21","doi-asserted-by":"crossref","unstructured":"P\u00e9rez-Hern\u00e1ndez F., Tabik S, Lamas A, Olmos R, Fujita H, Herrera F (2020) Object detection binary classifiers methodology based on deep learning to identify small objects handled similarly: Application in video surveillance. Knowledge-Based Systems, 105590","DOI":"10.1016\/j.knosys.2020.105590"},{"key":"1961_CR22","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1961_CR23","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, So Kweon I (2018) Cbam: Convolutional block attention module. In: proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1961_CR24","first-page":"105","volume":"193","author":"P Gao","year":"2020","unstructured":"Gao P, Yuan R, Wang F, Xiao L, Fujita H, Zhang Y (2020) Siamese attentional keypoint network for high performance visual tracking. Knowledge-Based Systems 193:105\u2013448","journal-title":"Knowledge-Based Systems"},{"key":"1961_CR25","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.ins.2019.12.084","volume":"517","author":"P Gao","year":"2020","unstructured":"Gao P, Zhang Q, Wang F, Xiao L, Fujita H, Zhang Y (2020) Learning reinforced attentional representation for end-to-end visual tracking. Information Sciences 517:52\u201367","journal-title":"Information Sciences"},{"key":"1961_CR26","doi-asserted-by":"crossref","unstructured":"Perazzi F, Pont-Tuset J, McWilliams B, Van Gool L, Gross M, Sorkine-Hornung A (2016) A benchmark dataset and evaluation methodology for video object segmentation. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 724\u2013732","DOI":"10.1109\/CVPR.2016.85"},{"key":"1961_CR27","doi-asserted-by":"crossref","unstructured":"Li F, Kim T, Humayun A, Tsai D, Rehg JM (2013) Video segmentation by tracking many figure-ground segments. In: proceedings of the IEEE International Conference on Computer Vision (pp. 2192\u20132199)","DOI":"10.1109\/ICCV.2013.273"},{"key":"1961_CR28","doi-asserted-by":"crossref","unstructured":"Rahtu E, Kannala J, Salo M, Heikkil\u00e4 J (2010) Segmenting salient objects from images and videos. In: European conference on computer vision (pp. 366\u2013379). Springer, Berlin, Heidelberg","DOI":"10.1007\/978-3-642-15555-0_27"},{"key":"1961_CR29","doi-asserted-by":"crossref","unstructured":"Zhou F, Bing Kang S, Cohen MF (2014) Time-mapping using space-time saliency. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3358\u20133365","DOI":"10.1109\/CVPR.2014.429"},{"issue":"9","key":"1961_CR30","doi-asserted-by":"publisher","first-page":"1522","DOI":"10.1109\/TCSVT.2014.2308642","volume":"24","author":"Z Liu","year":"2014","unstructured":"Liu Z, Zhang X, Luo S, Le Meur O (2014) Superpixel-based spatiotemporal saliency detection. IEEE transactions on circuits and systems for video technology 24(9):1522\u20131540","journal-title":"IEEE transactions on circuits and systems for video technology"},{"key":"1961_CR31","doi-asserted-by":"crossref","unstructured":"Zhang J, Sclaroff S, Lin Z, Shen X, Price B, Mech R (2015) Minimum barrier salient object detection at 80 fps. In: proceedings of the IEEE international conference on computer vision, pp 1404\u20131412","DOI":"10.1109\/ICCV.2015.165"},{"key":"1961_CR32","doi-asserted-by":"crossref","unstructured":"Zhang J, Sclaroff S, Lin Z, Shen X, Price B, Mech R (2015) Minimum barrier salient object detection at 80 fps. In: proceedings of the IEEE international conference on computer vision, pp 1404\u20131412","DOI":"10.1109\/ICCV.2015.165"},{"key":"1961_CR33","doi-asserted-by":"crossref","unstructured":"Tu WC, He S, Yang Q, Chien SY (2016) Real-time salient object detection with a minimum spanning tree. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp 2334\u20132342","DOI":"10.1109\/CVPR.2016.256"},{"issue":"12","key":"1961_CR34","doi-asserted-by":"publisher","first-page":"2527","DOI":"10.1109\/TCSVT.2016.2595324","volume":"27","author":"Z Liu","year":"2016","unstructured":"Liu Z, Li J, Ye L, Sun G, Shen L (2016) Saliency detection for unconstrained videos using superpixel-level graph and spatiotemporal propagation. IEEE transactions on circuits and systems for video technology 27(12):2527\u20132542","journal-title":"IEEE transactions on circuits and systems for video technology"},{"issue":"7","key":"1961_CR35","doi-asserted-by":"publisher","first-page":"3156","DOI":"10.1109\/TIP.2017.2670143","volume":"26","author":"C Chen","year":"2017","unstructured":"Chen C, Li S, Wang Y, Qin H, Hao A (2017) Video saliency detection via spatial-temporal fusion and low-rank coherency diffusion. IEEE Trans Image Process 26(7):3156\u20133170","journal-title":"IEEE Trans Image Process"},{"issue":"7","key":"1961_CR36","doi-asserted-by":"publisher","first-page":"1973","DOI":"10.1109\/TCSVT.2018.2859773","volume":"29","author":"Y Tang","year":"2018","unstructured":"Tang Y, Zou W, Jin Z, Chen Y, Hua Y, Li X (2018) Weakly supervised salient object detection with spatiotemporal cascade neural networks. IEEE Transactions on Circuits and Systems for Video Technology 29(7):1973\u20131984","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"1","key":"1961_CR37","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/TIP.2017.2754941","volume":"27","author":"W Wang","year":"2017","unstructured":"Wang W, Shen J, Shao L (2017) Video salient object detection via fully convolutional networks. IEEE Trans Image Process 27(1):38\u201349","journal-title":"IEEE Trans Image Process"},{"key":"1961_CR38","doi-asserted-by":"crossref","unstructured":"Li S, Seybold B, Vorobyov A, Lei X, Jay Kuo CC (2018) Unsupervised video object segmentation with motion-based bilateral networks. In: proceedings of the European Conference on Computer Vision (ECCV) (pp. 207\u2013223)","DOI":"10.1007\/978-3-030-01219-9_13"},{"key":"1961_CR39","doi-asserted-by":"crossref","unstructured":"Fan DP, Cheng MM, Liu Y, Li T, Borji A (2017) Structure-measure: a new way to evaluate foreground maps. In: proceedings of the IEEE international conference on computer vision, pp 4548\u20134557","DOI":"10.1109\/ICCV.2017.487"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-020-01961-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-020-01961-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-020-01961-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,20]],"date-time":"2021-05-20T08:07:33Z","timestamp":1621498053000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-020-01961-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,13]]},"references-count":39,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["1961"],"URL":"https:\/\/doi.org\/10.1007\/s10489-020-01961-4","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2020,11,13]]},"assertion":[{"value":"18 September 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2020","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}