{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T04:18:44Z","timestamp":1767845924737,"version":"3.49.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030110239","type":"print"},{"value":"9783030110246","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-11024-6_43","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T04:29:27Z","timestamp":1548304167000},"page":"560-574","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Visually Indicated Sound Generation by Perceptually Optimized Classification"],"prefix":"10.1007","author":[{"given":"Kan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanxi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaowen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trung","family":"Bui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ram","family":"Nevatia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,23]]},"reference":[{"key":"43_CR1","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"},{"key":"43_CR2","doi-asserted-by":"crossref","unstructured":"Chen, L., Srivastava, S., Duan, Z., Xu, C.: Deep cross-modal audio-visual generation. In: ACM MM Workshop (2017)","DOI":"10.1145\/3126686.3126723"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wang, Z., Fang, C., Bui, T., Berg, T.L.: Visual to sound: generating natural sound for videos in the wild. CoRR (2017)","DOI":"10.1109\/CVPR.2018.00374"},{"key":"43_CR4","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"43_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"43_CR6","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/TAU.1967.1161901","volume":"15","author":"P Welch","year":"1967","unstructured":"Welch, P.: The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms. IEEE Trans. Audio Electroacoust. 15, 70\u201373 (1967)","journal-title":"IEEE Trans. Audio Electroacoust."},{"key":"43_CR7","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: SoundNet: learning sound representations from unlabeled video. In: NIPS (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: ICASSP (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"43_CR9","unstructured":"Harwath, D., Torralba, A., Glass, J.: Unsupervised learning of spoken language with visual context. In: NIPS (2016)"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"43_CR11","unstructured":"Muthusamy, Y.K., Cole, R.A., Slaney, M.: Speaker-independent vowel recognition: spectrograms versus cochleagrams. In: ICASSP (1990)"},{"key":"43_CR12","unstructured":"Mehri, S., et al.: SampleRNN: an unconditional end-to-end neural audio generation model. In: ICLR (2016)"},{"key":"43_CR13","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: CVPR (2014)"},{"key":"43_CR14","unstructured":"Szegedy, C., et al.: Intriguing properties of neural networks. In: ICLR (2014)"},{"key":"43_CR15","unstructured":"Yosinski, J., Clune, J., Nguyen, A., Fuchs, T., Lipson, H.: Understanding neural networks through deep visualization. In: CVPR (2015)"},{"key":"43_CR16","doi-asserted-by":"crossref","unstructured":"Mahendran, A., Vedaldi, A.: Understanding deep image representations by inverting them. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"43_CR17","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Brox, T.: Inverting visual representations with convolutional networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.522"},{"key":"43_CR18","doi-asserted-by":"crossref","unstructured":"Chen, K., Bui, T., Fang, C., Wang, Z., Nevatia, R.: AMC: attention guided multi-modal correlation learning for image search. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.657"},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"43_CR20","unstructured":"Chen, K., Wang, J., Chen, L.C., Gao, H., Xu, W., Nevatia, R.: ABC-CNN: an attention based convolutional neural network for visual question answering. In: CVPRW (2016)"},{"key":"43_CR21","first-page":"17","volume":"7","author":"K Chen","year":"2018","unstructured":"Chen, K., Kovvuri, R., Gao, J., Nevatia, R.: MSRC: multimodal spatial regression with semantic context for phrase grounding. IJMIR 7, 17\u201328 (2018)","journal-title":"IJMIR"},{"key":"43_CR22","doi-asserted-by":"crossref","unstructured":"Chen, K., Kovvuri, R., Nevatia, R.: Query-guided regression network with context policy for phrase grounding. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.95"},{"key":"43_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/978-3-030-01216-8_5","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Gao","year":"2018","unstructured":"Gao, J., Chen, K., Nevatia, R.: CTAP: complementary temporal action proposal generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 70\u201385. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_5"},{"key":"43_CR24","unstructured":"Myers, G.K., et al.: The 2014 SESAME multimedia event detection and recounting system. In: Proceedings of TRECVID (2014)"},{"key":"43_CR25","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Sun, C., Chen, K., Nevatia, R.: TURN TAP: temporal unit regression network for temporal action proposals (2017)","DOI":"10.1109\/ICCV.2017.392"},{"key":"43_CR26","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"43_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"43_CR28","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"43_CR29","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/PROC.1978.10837","volume":"66","author":"FJ Harris","year":"1978","unstructured":"Harris, F.J.: On the use of windows for harmonic analysis with the discrete Fourier transform. Proc. IEEE 66, 51\u201383 (1978)","journal-title":"Proc. IEEE"},{"key":"43_CR30","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":"43_CR31","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"43_CR32","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: AISTATS (2010)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11024-6_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T01:08:23Z","timestamp":1674349703000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-11024-6_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030110239","9783030110246"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11024-6_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"23 January 2019","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"}]}}