{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:02:56Z","timestamp":1786978976906,"version":"3.56.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464473","type":"print"},{"value":"9783319464480","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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":[[2016]]},"DOI":"10.1007\/978-3-319-46448-0_48","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T04:27:24Z","timestamp":1474000044000},"page":"801-816","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":187,"title":["Ambient Sound Provides Supervision for Visual Learning"],"prefix":"10.1007","author":[{"given":"Andrew","family":"Owens","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josh H.","family":"McDermott","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William T.","family":"Freeman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Torralba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"48_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, P., Carreira, J., Malik, J.: Learning to see by moving. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.13"},{"key":"48_CR2","unstructured":"Andrew, G., Arora, R., Bilmes, J.A., Livescu, K.: Deep canonical correlation analysis. In: ICML (2013)"},{"key":"48_CR3","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":"48_CR4","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Springenberg, J.T., Riedmiller, M., Brox, T.: Discriminative unsupervised feature learning with convolutional neural networks. In: NIPS (2014)","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"48_CR6","doi-asserted-by":"crossref","unstructured":"Ellis, D.P., Zeng, X., McDermott, J.H.: Classifying soundtracks with audio texture features. In: ICASSP (2011)","DOI":"10.1109\/ICASSP.2011.5947699"},{"key":"48_CR7","doi-asserted-by":"crossref","unstructured":"Eronen, A.J., Peltonen, V.T., Tuomi, J.T., Klapuri, A.P., Fagerlund, S., Sorsa, T., Lorho, G., Huopaniemi, J.: Audio-based context recognition. In: IEEE TASLP (2006)","DOI":"10.1109\/TSA.2005.854103"},{"issue":"2","key":"48_CR8","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. IJCV 88(2), 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"48_CR9","unstructured":"Fisher III, J.W., Darrell, T., Freeman, W.T., Viola, P.A.: Learning joint statistical models for audio-visual fusion and segregation. In: NIPS (2000)"},{"issue":"1","key":"48_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1207\/s15326969eco0501_1","volume":"5","author":"WW Gaver","year":"1993","unstructured":"Gaver, W.W.: What in the world do we hear?: an ecological approach to auditory event perception. Ecol. Psychol. 5(1), 1\u201329 (1993)","journal-title":"Ecol. Psychol."},{"key":"48_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"48_CR12","unstructured":"Goroshin, R., Bruna, J., Tompson, J., Eigen, D., LeCun, Y.: Unsupervised feature learning from temporal data. arXiv preprint \n                      arXiv:1504.02518\n                      \n                     (2015)"},{"key":"48_CR13","unstructured":"Hershey, J.R., Movellan, J.R.: Audio vision: using audio-visual synchrony to locate sounds. In: NIPS (1999)"},{"key":"48_CR14","doi-asserted-by":"crossref","unstructured":"Indyk, P., Motwani, R.: Approximate nearest neighbors: towards removing the curse of dimensionality. In: STOC (1998)","DOI":"10.1145\/276698.276876"},{"key":"48_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"48_CR16","unstructured":"Isola, P., Zoran, D., Krishnan, D., Adelson, E.H.: Learning visual groups from co-occurrences in space and time. In: ICLR Workshop (2016)"},{"key":"48_CR17","doi-asserted-by":"crossref","unstructured":"Jayaraman, D., Grauman, K.: Learning image representations tied to ego-motion. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.166"},{"key":"48_CR18","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: MM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"48_CR19","unstructured":"Kidron, E., Schechner, Y.Y., Elad, M.: Pixels that sound. In: CVPR (2005)"},{"key":"48_CR20","unstructured":"Kr\u00e4henb\u00fchl, P., Doersch, C., Donahue, J., Darrell, T.: Data-dependent initializations of convolutional neural networks. In: ICLR (2016)"},{"key":"48_CR21","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"48_CR22","doi-asserted-by":"crossref","unstructured":"Le, Q.V., Ranzato, M.A., Monga, R., Devin, M., Chen, K., Corrado, G.S., Dean, J., Ng, A.Y.: Building high-level features using large scale unsupervised learning. In: ICML (2012)","DOI":"10.1109\/ICASSP.2013.6639343"},{"key":"48_CR23","doi-asserted-by":"crossref","unstructured":"Lee, K., Ellis, D.P., Loui, A.C.: Detecting local semantic concepts in environmental sounds using Markov model based clustering. In: ICASSP (2010)","DOI":"10.1109\/ICASSP.2010.5495915"},{"issue":"1","key":"48_CR24","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1023\/A:1011126920638","volume":"43","author":"T Leung","year":"2001","unstructured":"Leung, T., Malik, J.: Representing and recognizing the visual appearance of materials using three-dimensional textons. IJCV 43(1), 29\u201344 (2001)","journal-title":"IJCV"},{"issue":"5","key":"48_CR25","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1016\/j.neuron.2011.06.032","volume":"71","author":"JH McDermott","year":"2011","unstructured":"McDermott, J.H., Simoncelli, E.P.: Sound texture perception via statistics of the auditory periphery: evidence from sound synthesis. Neuron 71(5), 926\u2013940 (2011)","journal-title":"Neuron"},{"key":"48_CR26","unstructured":"Mishkin, D., Matas, J.: All you need is a good init. arXiv preprint \n                      arXiv:1511.06422\n                      \n                     (2015)"},{"key":"48_CR27","doi-asserted-by":"crossref","unstructured":"Mobahi, H., Collobert, R., Weston, J.: Deep learning from temporal coherence in video. In: ICML (2009)","DOI":"10.1145\/1553374.1553469"},{"key":"48_CR28","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: ICML (2011)"},{"key":"48_CR29","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Is object localization for free?-weakly-supervised learning with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"48_CR30","doi-asserted-by":"crossref","unstructured":"Owens, A., Isola, P., McDermott, J., Torralba, A., Adelson, E.H., Freeman, W.T.: Visually indicated sounds. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.264"},{"issue":"7","key":"48_CR31","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1016\/j.ijar.2008.11.006","volume":"50","author":"R Salakhutdinov","year":"2009","unstructured":"Salakhutdinov, R., Hinton, G.: Semantic hashing. Int. J. Approx. Reason. 50(7), 969\u2013978 (2009)","journal-title":"Int. J. Approx. Reason."},{"key":"48_CR32","unstructured":"Slaney, M., Covell, M.: Facesync: A linear operator for measuring synchronization of video facial images and audio tracks. In: NIPS (2000)"},{"key":"48_CR33","unstructured":"Srivastava, N., Salakhutdinov, R.R.: Multimodal learning with deep Boltzmann machines. In: NIPS (2012)"},{"key":"48_CR34","unstructured":"Thomee, B., Shamma, D.A., Friedland, G., Elizalde, B., Ni, K., Poland, D., Borth, D., Li, L.J.: The new data and new challenges in multimedia research. arXiv preprint \n                      arXiv:1503.01817\n                      \n                     (2015)"},{"key":"48_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Unsupervised learning of visual representations using videos. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.320"},{"key":"48_CR36","unstructured":"Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: NIPS (2009)"},{"key":"48_CR37","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"48_CR38","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Object detectors emerge in deep scene CNNs. In: ICLR 2015 (2014)"},{"key":"48_CR39","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: NIPS (2014)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46448-0_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T20:20:00Z","timestamp":1602274800000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46448-0_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464473","9783319464480"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46448-0_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","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":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.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"}]}}