{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T04:11:38Z","timestamp":1751947898915,"version":"3.41.2"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030007638"},{"type":"electronic","value":"9783030007645"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-00764-5_65","type":"book-chapter","created":{"date-parts":[[2018,9,17]],"date-time":"2018-09-17T16:21:31Z","timestamp":1537201291000},"page":"708-718","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Research on Multitask Deep Learning Network for Semantic Segmentation and Object Detection"],"prefix":"10.1007","author":[{"given":"Ting","family":"Rui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fukai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengsong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,18]]},"reference":[{"key":"65_CR1","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell. T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587. IEEE Computer Society (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"9","key":"65_CR2","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"65_CR3","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. Computer Science (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"65_CR4","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"65_CR5","unstructured":"Li, Y., He, K., Sun, J., et al.: R-fcn: Object detection via region based fully convolutional networks. In: Advances in Neural Information Processing Systems, pp. 379\u2013387 (2016)"},{"key":"65_CR6","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: Youonly look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"65_CR7","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger (2016). arXiv:1612.08242","DOI":"10.1109\/CVPR.2017.690"},{"key":"65_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"65_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"65_CR10","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"65_CR11","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with d deep convolutional encoder-decoder architecture for image segmeeep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097\u20131105. Curran Associates Inc. (2012)"},{"key":"65_CR12","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science (2014)"},{"key":"65_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, pp. 770\u2013778. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"99","key":"65_CR14","first-page":"1","volume":"PP","author":"V Badrinarayanan","year":"2015","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: antation. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"65_CR15","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., et al.: Pyramid scene parsing network (2016)","DOI":"10.1109\/CVPR.2017.660"},{"key":"65_CR16","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., et al.: DeepLab v3: rethinking atrous convolution for semantic image segmentation (2017)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"65_CR17","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., et al.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation (2016)","DOI":"10.1109\/CVPR.2017.549"},{"key":"65_CR18","doi-asserted-by":"crossref","unstructured":"Bul\u00f2, S.R., Neuhold, G., Kontschieder, P.: Loss max-pooling for semantic image segmentation (2017)","DOI":"10.1109\/CVPR.2017.749"},{"key":"65_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. arXiv preprint arXiv:1612.03144 (2016)","DOI":"10.1109\/CVPR.2017.106"},{"key":"65_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. arXiv preprint arXiv:1703.06870 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"issue":"7","key":"65_CR21","doi-asserted-by":"publisher","first-page":"1476","DOI":"10.1109\/TPAMI.2016.2601099","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Zhang, X., Sun, J.: Object detection networks on convolutional feature maps. IEEE Trans. Pattern Anal. Mach. Intell. 39(7), 1476\u20131481 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"65_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. arXiv preprint arXiv:1708.02002 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"issue":"2","key":"65_CR23","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The Pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"65_CR24","doi-asserted-by":"crossref","unstructured":"Pohlen, T., Hermans, A., Mathias, M., et al.: Full-resolution residual networks for semantic segmentation in street scenes, 3309\u20133318 (2017)","DOI":"10.1109\/CVPR.2017.353"},{"key":"65_CR25","unstructured":"Cheng, J., Liu, S., Tsai, Y.H., et al.: Learning to segment instances in videos with spatial propagation network (2017)"},{"key":"65_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"65_CR27","unstructured":"Huang, G., Liu, Z., Laurens, V.D.M., et al.: Densely connected convolutional networks, 2261\u20132269 (2016)"},{"key":"65_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V, et al.: Inception-v4, Inception-ResNet and the impact of residual connections on learning (2016)","DOI":"10.1609\/aaai.v31i1.11231"},{"issue":"9","key":"65_CR29","doi-asserted-by":"publisher","first-page":"4128","DOI":"10.1109\/TIP.2017.2710635","volume":"26","author":"R Hong","year":"2017","unstructured":"Hong, R., Li, L., Cai, J., Tao, D., Wang, M., Tian, Q.: Coherent semantic-visual indexing for large-scale image retrieval in the Cloud. IEEE Trans. Image Process. 26(9), 4128\u20134138 (2017)","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"65_CR30","doi-asserted-by":"publisher","first-page":"5814","DOI":"10.1109\/TIP.2016.2614132","volume":"25","author":"R Hong","year":"2016","unstructured":"Hong, R., Zhenzhen, H., Wang, R., Wang, M., Tao, D.: Multi-view object retrieval via multi-scale topic models. IEEE Trans. Image Process. 25(12), 5814\u20135827 (2016)","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"65_CR31","doi-asserted-by":"publisher","first-page":"1555","DOI":"10.1109\/TMM.2016.2567071","volume":"18","author":"R Hong","year":"2016","unstructured":"Hong, R., Zhang, L., Zhang, C., Zimmermann, R.: Flickr circles: aesthetic tendency discovery by multi-view regularized topic modeling. IEEE Trans. Multimed. 18(8), 1555\u20131567 (2016)","journal-title":"IEEE Trans. Multimed."}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Information Processing \u2013 PCM 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00764-5_65","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T16:27:13Z","timestamp":1751905633000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00764-5_65"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007638","9783030007645"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00764-5_65","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"18 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PCM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim Conference on Multimedia","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pcm2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pcm2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}