{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:19:52Z","timestamp":1771949992746,"version":"3.50.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012243","type":"print"},{"value":"9783030012250","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01225-0_22","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T08:39:54Z","timestamp":1538987994000},"page":"367-383","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["Attentive Semantic Alignment with Offset-Aware Correlation Kernels"],"prefix":"10.1007","author":[{"given":"Paul Hongsuck","family":"Seo","sequence":"first","affiliation":[]},{"given":"Jongmin","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Deunsol","family":"Jung","sequence":"additional","affiliation":[]},{"given":"Bohyung","family":"Han","sequence":"additional","affiliation":[]},{"given":"Minsu","family":"Cho","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"issue":"2","key":"22_CR1","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TPAMI.2012.156","volume":"35","author":"A Hosni","year":"2013","unstructured":"Hosni, A., Rhemann, C., Bleyer, M., Rother, C., Gelautz, M.: Fast cost-volume filtering for visual correspondence and beyond. IEEE Trans. Patt. Anal. Mach. Intell. 35(2), 504\u2013511 (2013)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"issue":"4","key":"22_CR2","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1109\/34.206955","volume":"15","author":"M Okutomi","year":"1993","unstructured":"Okutomi, M., Kanade, T.: A multiple-baseline stereo. IEEE Trans. Patt. Anal. Mach. Intell. 15(4), 353\u2013363 (1993)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: DeepFlow: large displacement optical flow with deep matching. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.175"},{"issue":"3","key":"22_CR5","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/s11263-016-0908-3","volume":"120","author":"J Revaud","year":"2016","unstructured":"Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: DeepMatching: hierarchical deformable dense matching. Int. J. Comput. Vis. 120(3), 300\u2013323 (2016)","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"22_CR6","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"22_CR7","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-319-23048-1_2","volume-title":"Dense Image Correspondences for Computer Vision","author":"C Liu","year":"2016","unstructured":"Liu, C., Yuen, J., Torralba, A.: SIFT flow: dense correspondence across scenes and its applications. In: Hassner, T., Liu, C. (eds.) Dense Image Correspondences for Computer Vision, pp. 15\u201349. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-23048-1_2"},{"key":"22_CR8","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Ham, B., Cho, M., Schmid, C., Ponce, J.: Proposal flow. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.378"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Taniai, T., Sinha, S.N., Sato, Y.: Joint recovery of dense correspondence and cosegmentation in two images. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.460"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Kim, J., Liu, C., Sha, F., Grauman, K.: Deformable spatial pyramid matching for fast dense correspondences. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.299"},{"key":"22_CR12","unstructured":"Choy, C.B., Gwak, J., Savarese, S., Chandraker, M.: Universal correspondence network. In: Advances in Neural Information Processing Systems, pp. 2414\u20132422 (2016)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Rocco, I., Arandjelovic, R., Sivic, J.: Convolutional neural network architecture for geometric matching. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.12"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Han, K., et al.: SCNet: learning semantic correspondence. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.203"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Ufer, N., Ommer, B.: Deep semantic feature matching. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.628"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Kim, S., Min, D., Lin, S., Sohn, K.: DCTM: discrete-continuous transformation matching for semantic flow. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.485"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Kim, S., Min, D., Ham, B., Jeon, S., Lin, S., Sohn, K.: FCSS: fully convolutional self-similarity for dense semantic correspondence. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.73"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Novotny, D., Larlus, D., Vedaldi, A.: AnchorNet: a weakly supervised network to learn geometry-sensitive features for semantic matching. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.306"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Learning to compare image patches via convolutional neural networks. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299064"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Zbontar, J., LeCun, Y.: Computing the stereo matching cost with a convolutional neural network. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298767"},{"key":"22_CR21","unstructured":"Han, X., Leung, T., Jia, Y., Sukthankar, R., Berg, A.C.: MatchNet: unifying feature and metric learning for patch-based matching. In: CVPR (2015)"},{"key":"22_CR22","unstructured":"Long, J.L., Zhang, N., Darrell, T.: Do convnets learn correspondence? In: NIPS (2014)"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Zhou, T., Krahenbuhl, P., Aubry, M., Huang, Q., Efros, A.A.: Learning dense correspondence via 3D-guided cycle consistency. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.20"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Jacobs, D.W., Chandraker, M.: WarpNet: weakly supervised matching for single-view reconstruction. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.354"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Yang, H., Lin, W.Y., Lu, J.: Daisy filter flow: a generalized discrete approach to dense correspondences. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.435"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Hur, J., Lim, H., Park, C., Chul Ahn, S.: Generalized deformable spatial pyramid: Geometry-preserving dense correspondence estimation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298745"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Bristow, H., Valmadre, J., Lucey, S.: Dense semantic correspondence where every pixel is a classifier. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.458"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Berg, A.C., Berg, T.L., Malik, J.: Shape matching and object recognition using low distortion correspondences. In: CVPR (2005)","DOI":"10.1007\/11957959_25"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Yang, F., Li, X., Cheng, H., Li, J., Chen, L.: Object-aware dense semantic correspondence. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.442"},{"key":"22_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1007\/978-3-642-15555-0_36","volume-title":"Computer Vision \u2013 ECCV 2010","author":"M Cho","year":"2010","unstructured":"Cho, M., Lee, J., Lee, K.M.: Reweighted random walks for graph matching. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 492\u2013505. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15555-0_36"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Duchenne, O., Joulin, A., Ponce, J.: A graph-matching kernel for object categorization. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126445"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Cho, M., Alahari, K., Ponce, J.: Learning graphs to match. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.11"},{"issue":"1\u201332","key":"22_CR33","first-page":"2","volume":"17","author":"J Zbontar","year":"2016","unstructured":"Zbontar, J., LeCun, Y.: Stereo matching by training a convolutional neural network to compare image patches. J. Mach. Learn. Res. 17(1\u201332), 2 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Luo, W., Schwing, A.G., Urtasun, R.: Efficient deep learning for stereo matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5695\u20135703 (2016)","DOI":"10.1109\/CVPR.2016.614"},{"key":"22_CR35","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Mun, J., Cho, M., Han, B.: Text-guided attention model for image captioning. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11237"},{"key":"22_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-319-46478-7_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Xu","year":"2016","unstructured":"Xu, H., Saenko, K.: Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 451\u2013466. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_28"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"22_CR39","unstructured":"Seo, P.H., Lin, Z., Cohen, S., Shen, X., Han, B.: Progressive attention networks for visual attribute prediction. arXiv preprint arXiv:1606.02393 (2016)"},{"key":"22_CR40","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: EMNLP (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Noh, H., Araujo, A., Sim, J., Weyand, T., Han, B.: Large-scale image retrieval with attentive deep local features. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.374"},{"key":"22_CR43","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"22_CR44","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: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"22_CR45","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"22_CR46","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2011 (VOC2011) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2011\/workshop\/index.html"},{"issue":"12","key":"22_CR47","doi-asserted-by":"publisher","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","volume":"35","author":"Y Yang","year":"2013","unstructured":"Yang, Y., Ramanan, D.: Articulated human detection with flexible mixtures of parts. IEEE Trans. Patt. Anal. Mach. Intell. 35(12), 2878\u20132890 (2013)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.572"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01225-0_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:10:42Z","timestamp":1665187842000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01225-0_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012243","9783030012250"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01225-0_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}