{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:35:36Z","timestamp":1742913336733,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030845285"},{"type":"electronic","value":"9783030845292"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-84529-2_43","type":"book-chapter","created":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T15:01:42Z","timestamp":1628521302000},"page":"510-521","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Audio-Visual Salient Object Detection"],"prefix":"10.1007","author":[{"given":"Shuaiyang","family":"Cheng","sequence":"first","affiliation":[]},{"given":"Liang","family":"Song","sequence":"additional","affiliation":[]},{"given":"Jingjing","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Shihui","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,9]]},"reference":[{"key":"43_CR1","doi-asserted-by":"publisher","unstructured":"Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural circuitry. In: Matters of Intelligence, pp. 115\u2013141. Springer, Cham (1987). https:\/\/doi.org\/10.1007\/978-94-009-3833-5_5","DOI":"10.1007\/978-94-009-3833-5_5"},{"issue":"12","key":"43_CR2","doi-asserted-by":"publisher","first-page":"2461","DOI":"10.1007\/s11432-011-4487-1","volume":"54","author":"T Huang","year":"2011","unstructured":"Huang, T., Tian, Y., Li, J., Yu, H.: Salient region detection and segmentation for general object recognition and image understanding. Sci. Chin. Inf. Sci. 54(12), 2461\u20132470 (2011)","journal-title":"Sci. Chin. Inf. Sci."},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Lian, G., Lai, J., Yuan, Y.: Fast pedestrian detection using a modified WLD detector in salient region. In: Proceedings 2011 International Conference on System Science and Engineering, pp. 564\u2013569. IEEE (2011)","DOI":"10.1109\/ICSSE.2011.5961966"},{"issue":"1","key":"43_CR4","first-page":"185","volume":"19","author":"C Guo","year":"2009","unstructured":"Guo, C., Zhang, L.: A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression. IEEE Trans. Image Process. 19(1), 185\u2013198 (2009)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"43_CR5","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.: Saliency-aware video compression. IEEE Trans. Image Process. 23(1), 19\u201333 (2013)","journal-title":"IEEE Trans. Image Process."},{"issue":"5","key":"43_CR6","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1109\/TCSVT.2013.2280096","volume":"24","author":"Z Ren","year":"2013","unstructured":"Ren, Z., Gao, S., Chia, L.T., Tsang, I.W.H.: Region-based saliency detection and its application in object recognition. IEEE Trans. Circuits Syst. Video Technol. 24(5), 769\u2013779 (2013)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"43_CR7","unstructured":"Zhang, D., Meng, D., Zhao, L., Han, J.: Bridging saliency detection to weakly supervised object detection based on self-paced curriculum learning. arXiv:1703.01290 (2017)"},{"issue":"5","key":"43_CR8","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1007\/s00371-016-1216-1","volume":"33","author":"A Kapoor","year":"2016","unstructured":"Kapoor, A., Biswas, K.K., Hanmandlu, M.: An evolutionary learning based fuzzy theoretic approach for salient object detection. Vis. Comput. 33(5), 665\u2013685 (2016). https:\/\/doi.org\/10.1007\/s00371-016-1216-1","journal-title":"Vis. Comput."},{"key":"43_CR9","doi-asserted-by":"crossref","unstructured":"Ma, Y.F., Lu, L., Zhang, H.J., Li, M.: A user attention model for video summarization. In: Proceedings of the Tenth ACM International Conference on Multimedia, pp. 533\u2013542 (2002)","DOI":"10.1145\/641007.641116"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Simakov, D., Caspi, Y., Shechtman, E., Irani, M.: Summarizing visual data using bidirectional similarity. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587842"},{"key":"43_CR11","doi-asserted-by":"crossref","unstructured":"Sugano, Y., Matsushita, Y., Sato, Y.: Calibration-free gaze sensing using saliency maps. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2667\u20132674. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539984"},{"issue":"3","key":"43_CR12","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1167\/14.3.29","volume":"14","author":"A Borji","year":"2014","unstructured":"Borji, A., Itti, L.: Defending yarbus: eye movements reveal observers\u2019 task. J. Vis. 14(3), 29 (2014)","journal-title":"J. Vis."},{"key":"43_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-58558-7_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Ren","year":"2020","unstructured":"Ren, S., Han, C., Yang, X., Han, G., He, S.: Tenet: triple excitation network for video salient object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 212\u2013228. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_13"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"Fan, D.P., Wang, W., Cheng, M.M., Shen, J.: Shifting more attention to video salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8554\u20138564 (2019)","DOI":"10.1109\/CVPR.2019.00875"},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"Wang, W., Shen, J., Guo, F., Cheng, M.M., Borji, A.: Revisiting video saliency: a large-scale benchmark and a new model. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4894\u20134903 (2018)","DOI":"10.1109\/CVPR.2018.00514"},{"key":"43_CR16","doi-asserted-by":"crossref","unstructured":"Tsiami, A., Koutras, P., Maragos, P.: Stavis: spatio-temporal audiovisual saliency network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4766\u20134776 (2020)","DOI":"10.1109\/CVPR42600.2020.00482"},{"key":"43_CR17","doi-asserted-by":"crossref","unstructured":"Wang, W., Lai, Q., Fu, H., Shen, J., Ling, H., Yang, R.: Salient object detection in the deep learning era: An in-depth survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)","DOI":"10.1109\/TPAMI.2021.3051099"},{"key":"43_CR18","unstructured":"Borji, A.: Saliency prediction in the deep learning era: Successes, limitations, and future challenges. arXiv:1810.03716 (2018)"},{"issue":"1","key":"43_CR19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-37186-2","volume":"9","author":"G Lee","year":"2019","unstructured":"Lee, G., Nho, K., Kang, B., Sohn, K.A., Kim, D.: Predicting Alzheimer\u2019s disease progression using multi-modal deep learning approach. Sci. Rep. 9(1), 1\u201312 (2019)","journal-title":"Sci. Rep."},{"issue":"11","key":"43_CR20","doi-asserted-by":"publisher","first-page":"1887","DOI":"10.1109\/TMM.2015.2476655","volume":"17","author":"A Wang","year":"2015","unstructured":"Wang, A., Lu, J., Cai, J., Cham, T.J., Wang, G.: Large-margin multi-modal deep learning for RGB-D object recognition. IEEE Trans. Multimedia 17(11), 1887\u20131898 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"43_CR21","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1016\/j.compag.2019.05.016","volume":"162","author":"J Gen\u00e9-Mola","year":"2019","unstructured":"Gen\u00e9-Mola, J., Vilaplana, V., Rosell-Polo, J.R., Morros, J.R., Ruiz-Hidalgo, J., Gregorio, E.: Multi-modal deep learning for Fuji apple detection using RGB-D cameras and their radiometric capabilities. Comput. Electron. Agric. 162, 689\u2013698 (2019)","journal-title":"Comput. Electron. Agric."},{"issue":"2","key":"43_CR22","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/s41095-019-0149-9","volume":"5","author":"A Borji","year":"2019","unstructured":"Borji, A., Cheng, M.-M., Hou, Q., Jiang, H., Li, J.: Salient object detection: a survey. Comput. Vis. Media 5(2), 117\u2013150 (2019). https:\/\/doi.org\/10.1007\/s41095-019-0149-9","journal-title":"Comput. Vis. Media"},{"issue":"11","key":"43_CR23","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254\u20131259 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"43_CR24","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1109\/TPAMI.2010.70","volume":"33","author":"T Liu","year":"2010","unstructured":"Liu, T., et al.: Learning to detect a salient object. IEEE Trans. Pattern Anal. Mach. Intell. 33(2), 353\u2013367 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"43_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)"},{"key":"43_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"43_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/978-3-030-58610-2_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D-P Fan","year":"2020","unstructured":"Fan, D.-P., Zhai, Y., Borji, A., Yang, J., Shao, L.: BBS-Net: RGB-D salient object detection with a bifurcated backbone strategy network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 275\u2013292. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_17"},{"key":"43_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-030-58610-2_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Luo","year":"2020","unstructured":"Luo, A., Li, X., Yang, F., Jiao, Z., Cheng, H., Lyu, S.: Cascade graph neural networks for rgb-d salient object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 346\u2013364. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_21"},{"key":"43_CR29","doi-asserted-by":"crossref","unstructured":"Ling, H.: Cross-modal weighting network for RGB-D salient object detection (2020)","DOI":"10.1007\/978-3-030-58520-4_39"},{"key":"43_CR30","doi-asserted-by":"crossref","unstructured":"Ji, W., Li, J., Zhang, M., Piao, Y., Lu, H.: Accurate rgb-d salient object detection via collaborative learning. arXiv:2007.11782 (2020)","DOI":"10.1007\/978-3-030-58523-5_4"},{"key":"43_CR31","unstructured":"Wirth, N.: Pascal-s: a subset and its implementation. Berichte des Instituts f\u00fcrInformatik, vol. 12 (1975)"},{"key":"43_CR32","doi-asserted-by":"crossref","unstructured":"Movahedi, V., Elder, J.H.: Design and perceptual validation of performance measures for salient object segmentation. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops, pp. 49\u201356. IEEE (2010)","DOI":"10.1109\/CVPRW.2010.5543739"},{"key":"43_CR33","doi-asserted-by":"crossref","unstructured":"Gao, R., Oh, T.H., Grauman, K., Torresani, L.: Listen to look: action recognition by previewing audio. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10457\u201310467 (2020)","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"43_CR34","doi-asserted-by":"crossref","unstructured":"Meishvili, G., Jenni, S., Favaro, P.: Learning to have an ear for face super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1364\u20131374 (2020)","DOI":"10.1109\/CVPR42600.2020.00144"},{"key":"43_CR35","unstructured":"Tavakoli, H.R., Borji, A., Rahtu, E., Kannala, J.: Dave: A deep audio-visual embedding for dynamic saliency prediction. arXiv:1905.10693 (2019)"},{"key":"43_CR36","unstructured":"Jain, S., Yarlagadda, P., Subramanian, R., Gandhi, V.: Avinet: Diving deep into audio-visual saliency prediction. arXiv:2012.06170 (2020)"},{"key":"43_CR37","unstructured":"Tomar, S.: Converting video formats with FFmpeg. Linux J. 2006(146), 10 (2006)"},{"key":"43_CR38","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: Soundnet: Learning sound representations from unlabeled video. arXiv:1610.09001 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"43_CR39","unstructured":"Cheng, S., Gao, X., Song, L., Xiahou, J.: Audio-visual saliency network with audio attention module, unpublished"},{"key":"43_CR40","doi-asserted-by":"crossref","unstructured":"Fan, D., Cheng, M., Liu, Y., Li, T., Borji, A.: A new way to evaluate foreground maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p. 245484557 (2017)","DOI":"10.1109\/ICCV.2017.487"},{"key":"43_CR41","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Kr\u00e4henb\u00fchl, P., Pritch, Y., Hornung, A.: Saliency filters: contrast based filtering for salient region detection. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 733\u2013740. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247743"},{"key":"43_CR42","doi-asserted-by":"crossref","unstructured":"Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1597\u20131604. IEEE (2009)","DOI":"10.1109\/CVPRW.2009.5206596"}],"container-title":["Lecture Notes in Computer Science","Intelligent Computing Theories and Application"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-84529-2_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:07:54Z","timestamp":1710256074000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-84529-2_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030845285","9783030845292"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-84529-2_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"9 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2021a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2021\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}