{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T02:33:50Z","timestamp":1778812430915,"version":"3.51.4"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/wacv45572.2020.9093452","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"1596-1605","source":"Crossref","is-referenced-by-count":15,"title":["Visual Question Answering on 360\u00b0 Images"],"prefix":"10.1109","author":[{"given":"Shih-Han","family":"Chou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Lun","family":"Chao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Sheng","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","author":"su","year":"2019"},{"key":"ref38","article-title":"Pythia-a platform for vision & language research","author":"singh","year":"2018","journal-title":"SysML Workshop NeurIPS volume 2018"},{"key":"ref33","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref32","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"li","year":"2019"},{"key":"ref31","article-title":"Semantic-driven generation of hyperlapse from 360° video","author":"lai","year":"2017","journal-title":"TVCG"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref37","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref36","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref35","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"NIPS"},{"key":"ref34","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"NIPS"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12289","article-title":"Self-view grounding given a narrated 360° Video","author":"chou","year":"2018","journal-title":"AAAI"},{"key":"ref40","article-title":"Learning spherical convolution for fast features from 360° imagery","author":"su","year":"2017","journal-title":"NIPS"},{"key":"ref11","article-title":"360-indoor: Towards learning real-world objects in 360° indoor equirectangular images","author":"chou","year":"2019"},{"key":"ref12","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"},{"key":"ref13","article-title":"Embodied question answering","author":"das","year":"2018","journal-title":"CVPR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_48"},{"key":"ref15","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref17","article-title":"Are you talking to a machine? dataset and methods for multilingual image question","author":"gao","year":"2015","journal-title":"NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref28","article-title":"Skip-thought vectors","author":"kiros","year":"2015","journal-title":"NIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref3","article-title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","author":"armeni","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1040"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982405"},{"key":"ref5","article-title":"Matterport3D: Learning from RGB-D data in indoor environments","author":"chang","year":"2017","journal-title":"3DV"},{"key":"ref8","article-title":"Uniter: Learning universal image-text representations","author":"chen","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00154"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.283"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.1986.276658"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.153"},{"key":"ref47","article-title":"Leveraging video descriptions to learn video question answering","author":"zeng","year":"2017","journal-title":"AAAI"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","article-title":"Pano2Vid: Automatic cinematography for watching 360° videos","author":"su","year":"2016","journal-title":"ACCV"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00816"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref44","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"ICML"},{"key":"ref26","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"ICLRE"},{"key":"ref43","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref25","article-title":"Show, ask, attend, and answer: A strong baseline for visual question answering","author":"kazemi","year":"2017"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","location":"Snowmass Village, CO, USA","start":{"date-parts":[[2020,3,1]]},"end":{"date-parts":[[2020,3,5]]}},"container-title":["2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9087828\/9093261\/09093452.pdf?arnumber=9093452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T19:44:00Z","timestamp":1666554240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093452","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}