{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T16:27:42Z","timestamp":1726849662370},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319972886"},{"type":"electronic","value":"9783319972893"}],"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\/978-3-319-97289-3_16","type":"book-chapter","created":{"date-parts":[[2018,7,26]],"date-time":"2018-07-26T11:28:07Z","timestamp":1532604487000},"page":"211-220","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Selective Comprehension for Referring Expression by Prebuilt Entity Dictionary with Modular Networks"],"prefix":"10.1007","author":[{"given":"Enjie","family":"Cui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayu","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanghao","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,7,27]]},"reference":[{"key":"16_CR1","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. arXiv preprint \narXiv:1412.7755\n\n (2014)"},{"key":"16_CR2","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, pp. 379\u2013387 (2016)"},{"key":"16_CR3","doi-asserted-by":"publisher","unstructured":"Hu, R., Rohrbach, M., Andreas, J., Darrell, T., Saenko, K.: Modeling relationships in referential expressions with compositional modular networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4418\u20134427, July 2017. \nhttps:\/\/doi.org\/10.1109\/CVPR.2017.470","DOI":"10.1109\/CVPR.2017.470"},{"key":"16_CR4","doi-asserted-by":"publisher","unstructured":"Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., Darrell, T.: Natural language object retrieval. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4555\u20134564, June 2016. \nhttps:\/\/doi.org\/10.1109\/CVPR.2016.493","DOI":"10.1109\/CVPR.2016.493"},{"key":"16_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1007\/978-3-319-10602-1_47","volume-title":"Computer Vision \u2013 ECCV 2014","author":"P Kr\u00e4henb\u00fchl","year":"2014","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Geodesic object proposals. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 725\u2013739. Springer, Cham (2014). \nhttps:\/\/doi.org\/10.1007\/978-3-319-10602-1_47"},{"key":"16_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). \nhttps:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"16_CR7","doi-asserted-by":"publisher","unstructured":"Liu, J., Wang, L., Yang, M.H.: Referring expression generation and comprehension via attributes. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4866\u20134874, October 2017. \nhttps:\/\/doi.org\/10.1109\/ICCV.2017.520","DOI":"10.1109\/ICCV.2017.520"},{"key":"16_CR8","doi-asserted-by":"publisher","unstructured":"Luo, R., Shakhnarovich, G.: Comprehension-guided referring expressions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3125\u20133134, July 2017. \nhttps:\/\/doi.org\/10.1109\/CVPR.2017.333","DOI":"10.1109\/CVPR.2017.333"},{"key":"16_CR9","doi-asserted-by":"publisher","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11\u201320, June 2016. \nhttps:\/\/doi.org\/10.1109\/CVPR.2016.9","DOI":"10.1109\/CVPR.2016.9"},{"key":"16_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1007\/978-3-319-46493-0_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"VK Nagaraja","year":"2016","unstructured":"Nagaraja, V.K., Morariu, V.I., Davis, L.S.: Modeling context between objects for referring expression understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 792\u2013807. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46493-0_48"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"16_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/978-3-319-46448-0_49","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Rohrbach","year":"2016","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 817\u2013834. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46448-0_49"},{"issue":"2","key":"16_CR13","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"16_CR14","doi-asserted-by":"publisher","unstructured":"Yu, L., Tan, H., Bansal, M., Berg, T.L.: A joint speaker-listener-reinforcer model for referring expressions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3521\u20133529, July 2017. \nhttps:\/\/doi.org\/10.1109\/CVPR.2017.375","DOI":"10.1109\/CVPR.2017.375"},{"key":"16_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"16_CR16","doi-asserted-by":"publisher","unstructured":"Zhu, Y., Groth, O., Bernstein, M., Fei-Fei, L.: Visual7W: grounded question answering in images. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4995\u20135004, June 2016. \nhttps:\/\/doi.org\/10.1109\/CVPR.2016.540","DOI":"10.1109\/CVPR.2016.540"},{"key":"16_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391\u2013405. Springer, Cham (2014). \nhttps:\/\/doi.org\/10.1007\/978-3-319-10602-1_26"},{"issue":"6","key":"16_CR18","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Knowledge Management and Acquisition for Intelligent Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-97289-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,7,26]],"date-time":"2018-07-26T11:37:40Z","timestamp":1532605060000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-97289-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319972886","9783319972893"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-97289-3_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}