{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:27:06Z","timestamp":1730266026833,"version":"3.28.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191383","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["3DSEAVNet: 3D-Squeeze-and-Excitation Networks for Audio-Visual Saliency Prediction"],"prefix":"10.1109","author":[{"given":"Silong","family":"Liang","sequence":"first","affiliation":[{"name":"College of Software Engineering, JiLin University,Changchun,China"}]},{"given":"Chunxiao","family":"Li","sequence":"additional","affiliation":[{"name":"College of Software Engineering, JiLin University,Changchun,China"}]},{"given":"Naying","family":"Cui","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, JiLin University,Changchun,China"}]},{"given":"Minghui","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, JiLin University,Changchun,China"}]},{"given":"Hao","family":"Xue","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, JiLin University,Changchun,China"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Dave: A deep audio-visual embedding for dynamic saliency prediction","author":"tavakoli","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00482"},{"key":"ref12","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Environment Sound Classification using Multiple Feature Channels and Deep Convolutional Neural Networks[J]","volume":"4","author":"sharma","year":"2019","journal-title":"J of Elec Systems Science and Engineering"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-3435-5_16"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1167\/14.8.5"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref30","article-title":"So Kweon.CBAM: Convolutional Block Attention Module[A]","author":"woo","year":"2018","journal-title":"Computer Vision 15th European Conference (ECCV 2018)[C]"},{"key":"ref11","first-page":"2394","article-title":"Corso, Tased-net: temporally-aggregating spatial encoder decoder network for video saliency detection","author":"min","year":"2019","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref33","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref10","first-page":"11","article-title":"Spatio Temporal Sa liency Netw orks for Dynamic Sali ency Prediction[J]","author":"bak","year":"2016","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref32","first-page":"305","article-title":"Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification","author":"xie","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2895411"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.196"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"ref39","first-page":"1153","article-title":"Saliency and human fixations: dtate-of-the-art and study of comparison metrics","author":"riche","year":"2013","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.86"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-010-9074-z"},{"key":"ref19","first-page":"28","article-title":"Improved Adaptive Gaussian Mixture Model forBatkground Subtraction[C]","author":"zivkovic","year":"2004","journal-title":"Internation Conference on Pattern Recognition"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635989"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506089"},{"key":"ref23","article-title":"Dave: A deep audio-visual embedding for dynamic saliency prediction","author":"tavakoli","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref45","article-title":"Deep gaze I: Boosting saliency prediction with feature maps trained on imagenet","author":"k\u00fcmmerer","year":"2015","journal-title":"Conf on Learning Representations Workshop (ICLR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref47","article-title":"DeepSEED: 3D Squeeze-and-Excitation Encoder-Decoder Convolutional Neural Networks for Pulmonary Nodule Detection[J]","author":"li","year":"2019","journal-title":"ArXiv e-prints"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_27"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2815601"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.358"},{"key":"ref21","first-page":"1","article-title":"Spatio Temporal Saliency Netw orks for Dynamic Saliency Prediction[J]","volume":"1","author":"bak","year":"2016","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106998"},{"key":"ref28","first-page":"2017","article-title":"Spatial transformer networks[C]","author":"jaderberg","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref27","article-title":"Recurrent Models of Visual Attention[J]","author":"mnih","year":"2014","journal-title":"Computer Science"},{"key":"ref29","article-title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks[A]","author":"hu","year":"2018","journal-title":"Neural Information Processing Systems (NIPS) Conference"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1167\/8.5.2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1167\/14.8.5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2018.8499257"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240677"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366154"},{"key":"ref5","first-page":"185","article-title":"A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression","volume":"19","author":"guo","year":"2009","journal-title":"IEEE Trans Image Process"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191383.pdf?arnumber=10191383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:46:22Z","timestamp":1692639982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191383","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}