{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:20:15Z","timestamp":1742988015544,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"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_68","type":"book-chapter","created":{"date-parts":[[2018,9,17]],"date-time":"2018-09-17T16:21:31Z","timestamp":1537201291000},"page":"740-749","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text to Region: Visual-Word Guided Saliency Detection"],"prefix":"10.1007","author":[{"given":"Tengfei","family":"Xing","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaohui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunping","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,18]]},"reference":[{"key":"68_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"68_CR2","doi-asserted-by":"crossref","unstructured":"Cao, C., et al.: Look and think twice: capturing top-down visual attention with feedback convolutional neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2956\u20132964 (2015)","DOI":"10.1109\/ICCV.2015.338"},{"key":"68_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Lawrence Zitnick, C.: Mind\u2019s eye: a recurrent visual representation for image caption generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2422\u20132431 (2015)","DOI":"10.1109\/CVPR.2015.7298856"},{"issue":"3","key":"68_CR4","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/TPAMI.2014.2345401","volume":"37","author":"MM Cheng","year":"2015","unstructured":"Cheng, M.M., Mitra, N.J., Huang, X., Torr, P.H., Hu, S.M.: Global contrast based salient region detection. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 569\u2013582 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"68_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248\u2013255. IEEE, Washington (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"68_CR6","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 6 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"68_CR7","doi-asserted-by":"crossref","unstructured":"Mahendran, A., Vedaldi, A.: Understanding deep image representations by inverting them (2015)","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"68_CR8","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2641\u20132649. IEEE (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"68_CR9","doi-asserted-by":"crossref","unstructured":"Ramanishka, V., Das, A., Zhang, J., Saenko, K.: Top-down visual saliency guided by captions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, p. 7 (2017)","DOI":"10.1109\/CVPR.2017.334"},{"key":"68_CR10","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"68_CR11","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"68_CR12","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. arXiv preprint arXiv:1412.4729 (2014)","DOI":"10.3115\/v1\/N15-1173"},{"key":"68_CR13","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164. IEEE, Washington (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"68_CR14","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5288\u20135296. IEEE, Washington (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"68_CR15","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"68_CR16","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Describing videos by exploiting temporal structure. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"68_CR17","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"68_CR18","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., Tao, D.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of IEEE International Conference on Computer Visualization, vol. 3 (2017)","DOI":"10.1109\/ICCV.2017.202"},{"key":"68_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"68_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/978-3-319-46493-0_33","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Zhang","year":"2016","unstructured":"Zhang, J., Lin, Z., Brandt, J., Shen, X., Sclaroff, S.: Top-down neural attention by excitation backprop. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 543\u2013559. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_33"},{"key":"68_CR21","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921\u20132929. IEEE, Washington (2016)","DOI":"10.1109\/CVPR.2016.319"},{"issue":"11","key":"68_CR22","doi-asserted-by":"publisher","first-page":"3308","DOI":"10.1109\/TIP.2015.2438546","volume":"24","author":"L Zhou","year":"2015","unstructured":"Zhou, L., Yang, Z., Yuan, Q., Zhou, Z., Hu, D.: Salient region detection via integrating diffusion-based compactness and local contrast. IEEE Trans. Image Process. 24(11), 3308\u20133320 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"68_CR23","doi-asserted-by":"crossref","unstructured":"Zhu, W., Liang, S., Wei, Y., Sun, J.: Saliency optimization from robust background detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2814\u20132821 (2014)","DOI":"10.1109\/CVPR.2014.360"}],"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_68","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:17:15Z","timestamp":1710332235000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00764-5_68"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007638","9783030007645"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00764-5_68","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"}}]}}