{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T12:53:42Z","timestamp":1760705622374,"version":"3.40.3"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030012274"},{"type":"electronic","value":"9783030012281"}],"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\/978-3-030-01228-1_48","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T05:03:51Z","timestamp":1538802231000},"page":"808-831","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Visual Reasoning with Multi-hop Feature Modulation"],"prefix":"10.1007","author":[{"given":"Florian","family":"Strub","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathieu","family":"Seurin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ethan","family":"Perez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harm","family":"de Vries","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00e9r\u00e9mie","family":"Mary","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philippe","family":"Preux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Courville","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Pietquin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"48_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"48_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. In: Deep Learning Symposium (NIPS) (2016)"},{"key":"48_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of ICLR (2015)"},{"key":"48_CR4","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: Proceedings of ICML (2015)"},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual dialog. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"48_CR6","doi-asserted-by":"crossref","unstructured":"De Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., Courville, A.: Guesswhat?! Visual object discovery through multi-modal dialogue. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.475"},{"key":"48_CR7","unstructured":"Delbrouck, J.B., Dupont, S.: Modulating and attending the source image during encoding improves multimodal translation. In: Visually-Grounded Interaction and Language Workshop (NIPS) (2017)"},{"key":"48_CR8","unstructured":"Dumoulin, V., Shlens, J., Kudlur, M.: A learned representation for artistic style. In: Proceedings of ICLR (2017)"},{"key":"48_CR9","doi-asserted-by":"publisher","unstructured":"Dumoulin, V., et al.: Feature-wise transformations. Distill (2018). https:\/\/doi.org\/10.23915\/distill.00011, https:\/\/distill.pub\/2018\/feature-wise-transformations","DOI":"10.23915\/distill.00011"},{"issue":"2","key":"48_CR10","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., 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":"48_CR11","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. In: Proceedings of EMNLP (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"48_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of of CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"48_CR13","unstructured":"Graves, A., Wayne, G., Danihelka, I.: Neural turing machines. arXiv preprint arXiv:1410.5401 (2014)"},{"issue":"7626","key":"48_CR14","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/nature20101","volume":"538","author":"A Graves","year":"2016","unstructured":"Graves, A., et al.: Hybrid computing using a neural network with dynamic external memory. Nature 538(7626), 471 (2016)","journal-title":"Nature"},{"key":"48_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"48_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-319-46448-0_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Hu","year":"2016","unstructured":"Hu, R., Rohrbach, M., Darrell, T.: Segmentation from natural language expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 108\u2013124. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_7"},{"key":"48_CR17","doi-asserted-by":"crossref","unstructured":"Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., Darrell, T.: Natural language object retrieval. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2016.493"},{"key":"48_CR18","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. In: Proceedings of ICL (2018)"},{"key":"48_CR19","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of ICML (2015)"},{"key":"48_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1007\/978-3-319-46484-8_44","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Jabri","year":"2016","unstructured":"Jabri, A., Joulin, A., van der Maaten, L.: Revisiting visual question answering baselines. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 727\u2013739. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_44"},{"key":"48_CR21","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"48_CR22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.cviu.2017.06.005","volume":"163","author":"K Kafle","year":"2017","unstructured":"Kafle, K., Kanan, C.: Visual question answering: datasets, algorithms, and future challenges. Comput. Vis. Image Underst. 163, 3\u201320 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"48_CR23","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferitGame: referring to objects in photographs of natural scenes. In: Proceedings of EMNLP (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"48_CR24","unstructured":"Kim, J.H., On, K.W., Lim, W., Kim, J., Ha, J.W., Zhang, B.T.: Hadamard product for low-rank bilinear pooling. In: Proceedings of ICLR (2017)"},{"key":"48_CR25","unstructured":"Kim, J.H., et al.: Multimodal residual learning for visual QA. In: Proceedings of NIPS (2016)"},{"key":"48_CR26","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of ICLR (2014)"},{"key":"48_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of of NIPS (2012)"},{"key":"48_CR28","unstructured":"Lee, S.W., Heo, Y.J., Zhang, B.T.: Answerer in questioner\u2019s mind for goal-oriented visual dialogue. In: Visually-Grounded Interaction and Language Workshop (NIPS) (2018)"},{"key":"48_CR29","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). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"48_CR30","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"48_CR31","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: Proceedings of NIPS (2016)"},{"key":"48_CR32","doi-asserted-by":"crossref","unstructured":"Luo, R., Shakhnarovich, G.: Comprehension-guided referring expressions. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.333"},{"key":"48_CR33","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of EMNLP (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"48_CR34","doi-asserted-by":"crossref","unstructured":"Malinowski, M., Rohrbach, M., Fritz, M.: Ask your neurons: a neural-based approach to answering questions about images. In: Proceedings of ICCV (2015)","DOI":"10.1109\/ICCV.2015.9"},{"key":"48_CR35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15181-1","volume-title":"ImageCLEF: Experimental Evaluation in Visual Information Retrieval","author":"H Mller","year":"2012","unstructured":"Mller, H., Clough, P., Deselaers, T., Caputo, B.: ImageCLEF: Experimental Evaluation in Visual Information Retrieval. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-15181-1"},{"key":"48_CR36","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). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_48"},{"key":"48_CR37","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of ICML (2010)"},{"key":"48_CR38","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: Film: visual reasoning with a general conditioning layer. In: Proceedings of AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"48_CR39","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). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_49"},{"key":"48_CR40","doi-asserted-by":"crossref","unstructured":"Rupprecht, C., Laina, I., Navab, N., Hager, G.D., Tombari, F.: Guide me: interacting with deep networks. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00892"},{"issue":"3","key":"48_CR41","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"48_CR42","doi-asserted-by":"crossref","unstructured":"Strub, F., De Vries, H., Mary, J., Piot, B., Courville, A., Pietquin, O.: End-to-end optimization of goal-driven and visually grounded dialogue systems. In: Proceedings of IJCAI (2017)","DOI":"10.24963\/ijcai.2017\/385"},{"key":"48_CR43","unstructured":"Sukhbaatar, S., Weston, J., Fergus, R., et al.: End-to-end memory networks. In: Proceedings of NIPS (2015)"},{"key":"48_CR44","unstructured":"de Vries, H., Strub, F., Mary, J., Larochelle, H., Pietquin, O., Courville, A.C.: Modulating early visual processing by language. In: Proceedings of NIPS (2017)"},{"key":"48_CR45","unstructured":"Weston, J., Chopra, S., Bordes, A.: Memory networks. arXiv preprint arXiv:1410.3916 (2014)"},{"key":"48_CR46","unstructured":"Xiong, C., Merity, S., Socher, R.: Dynamic memory networks for visual and textual question answering. In: Proceedings of ICML (2016)"},{"key":"48_CR47","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":"48_CR48","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of ICML (2015)"},{"key":"48_CR49","doi-asserted-by":"crossref","unstructured":"Yang, L., Wang, Y., Xiong, X., Yang, J., Katsaggelos, A.K.: Efficient video object segmentation via network modulation. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00680"},{"key":"48_CR50","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MAttNet: modular attention network for referring expression comprehension. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"48_CR51","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). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"48_CR52","doi-asserted-by":"crossref","unstructured":"Yu, L., Tan, H., Bansal, M., Berg, T.L.: A joint speakerlistener-reinforcer model for referring expressions. In: Proceedings of CVPR (2016)","DOI":"10.1109\/CVPR.2017.375"},{"key":"48_CR53","unstructured":"Zhu, Y., Zhang, S., Metaxas, D.: Reasoning about fine-grained attribute phrases using reference games. In: Visually-Grounded Interaction and Language Workshop (NIPS) (2017)"},{"key":"48_CR54","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Wu, Q., Shen, C., Reid, I.D., van den Hengel, A.: Parallel attention: a unified framework for visual object discovery through dialogs and queries. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00447"}],"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\/978-3-030-01228-1_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:34:32Z","timestamp":1665016472000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01228-1_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012274","9783030012281"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01228-1_48","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":"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"}]}}