{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T15:05:17Z","timestamp":1790003117408,"version":"4.0.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,5,2]],"date-time":"2020-05-02T00:00:00Z","timestamp":1588377600000},"content-version":"vor","delay-in-days":366,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1565978"],"award-info":[{"award-number":["1565978"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,5,2]]},"DOI":"10.1145\/3290605.3300851","type":"proceedings-article","created":{"date-parts":[[2019,4,29]],"date-time":"2019-04-29T13:36:58Z","timestamp":1556545018000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Audible Panorama"],"prefix":"10.1145","author":[{"given":"Haikun","family":"Huang","sequence":"first","affiliation":[{"name":"University of Massachusetts, Boston, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Solah","sequence":"additional","affiliation":[{"name":"University of Massachusetts, Boston, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingzeyu","family":"Li","sequence":"additional","affiliation":[{"name":"Adobe Research & Columbia University, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lap-Fai","family":"Yu","sequence":"additional","affiliation":[{"name":"George Mason University, Fairfax, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,5,2]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3027063.3053211"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","unstructured":"Durand R Begault and Leonard J Trejo. 2000. 3-D sound for virtual reality and multimedia. (2000).","DOI":"10.5555\/184407"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2007.257"},{"key":"e_1_3_2_2_4_1","volume-title":"Perspectives on Potential of Sound in Virtual Environments. HAVE 2007. IEEE International Workshop on Haptic, Audio and Visual Environments and Games","author":"Dodiya Janki","year":"2007","unstructured":"Janki Dodiya and Vassil N. Alexandrov. 2007. Perspectives on Potential of Sound in Virtual Environments. HAVE 2007. IEEE International Workshop on Haptic, Audio and Visual Environments and Games (2007), 15--20."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858065"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471747"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858040"},{"key":"e_1_3_2_2_9_1","volume-title":"Deep Residual Learning for Image Recognition. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/pres.1996.5.3.290"},{"key":"e_1_3_2_2_11_1","volume-title":"Speed\/Accuracy Trade-Offs for Modern Convolutional Object Detectors. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","author":"Huang Jonathan","year":"2017","unstructured":"Jonathan Huang, Vivek Rathod, Chen Sun, Menglong Zhu, Anoop Korattikara, Alireza Fathi, Ian Fischer, Zbigniew Wojna, Yang Song, Sergio Guadarrama, and Kevin Murphy. 2017. Speed\/Accuracy Trade-Offs for Modern Convolutional Object Detectors. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21--26, 2017. 3296--3297."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04052-8_16"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858078"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201391"},{"key":"e_1_3_2_2_15_1","volume-title":"Microsoft COCO: Common Objects in Context. eprint arXiv 1405.0312","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, and Piotr Doll\u00c3ar. 2014. Microsoft COCO: Common Objects in Context. eprint arXiv 1405.0312 (2014)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025757"},{"key":"e_1_3_2_2_17_1","volume-title":"Summary statistics in auditory perception. Nature neuroscience 16, 4","author":"McDermott Josh H","year":"2013","unstructured":"Josh H McDermott, Michael Schemitsch, and Eero P Simoncelli. 2013. Summary statistics in auditory perception. Nature neuroscience 16, 4 (2013), 493--498."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","unstructured":"Pedro Morgado Nuno Vasconcelos Timothy Langlois and Oliver Wang. 2018. Self-Supervised Generation of Spatial Audio for 360\u00b0Video. In Neural Information Processing Systems (NeurIPS).","DOI":"10.5555\/3326943.3326977"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126659"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/545261.545290"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2203809"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126636"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025581"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778805"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173902"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2670291.2670295"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173717"},{"key":"e_1_3_2_2_28_1","volume-title":"2017 IEEE Winter Applications of Computer Vision Workshops (WACVW). 58--66","author":"Sharma K.","unstructured":"K. Sharma, A. C. Kumar, and S. M. Bhandarkar. 2017. Action Recognition in Still Images Using Word Embeddings from Natural Language Descriptions. In 2017 IEEE Winter Applications of Computer Vision Workshops (WACVW). 58--66."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-2466.1992.tb00812.x"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025519"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2788196"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1612524113"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"e_1_3_2_2_34_1","volume-title":"Sizing up human height variation. Nature genetics 40, 5","author":"Visscher Peter M","year":"2008","unstructured":"Peter M Visscher. 2008. Sizing up human height variation. Nature genetics 40, 5 (2008), 489."},{"key":"e_1_3_2_2_35_1","article-title":"The Influence of Background Music of Video Games on Immersion","volume":"5","author":"Zhang Jiulin","year":"2015","unstructured":"Jiulin Zhang and Xiaoqing Fu. 2015. The Influence of Background Music of Video Games on Immersion. Journal of Psychology and Psychotherapy 5, 191 (2015).","journal-title":"Journal of Psychology and Psychotherapy"},{"key":"e_1_3_2_2_36_1","volume-title":"Temporal Action Detection with Structured Segment Networks. CoRR abs\/1704.06228","author":"Zhao Yue","year":"2017","unstructured":"Yue Zhao, Yuanjun Xiong, Limin Wang, Zhirong Wu, Dahua Lin, and Xiaoou Tang. 2017. Temporal Action Detection with Structured Segment Networks. CoRR abs\/1704.06228 (2017)."}],"event":{"name":"CHI '19: CHI Conference on Human Factors in Computing Systems","location":"Glasgow Scotland Uk","acronym":"CHI '19","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3290605.3300851","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3290605.3300851","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3290605.3300851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T14:32:23Z","timestamp":1790001143000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3290605.3300851"}},"subtitle":["Automatic Spatial Audio Generation for Panorama Imagery"],"short-title":[],"issued":{"date-parts":[[2019,5,2]]},"references-count":36,"alternative-id":["10.1145\/3290605.3300851","10.1145\/3290605"],"URL":"https:\/\/doi.org\/10.1145\/3290605.3300851","relation":{},"subject":[],"published":{"date-parts":[[2019,5,2]]},"assertion":[{"value":"2019-05-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}