{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:20:37Z","timestamp":1750220437445,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,23]],"date-time":"2020-10-23T00:00:00Z","timestamp":1603411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Ministry of Science and Technology of Taiwan","award":["109-2634-F-002-027- ,109-2634-F-002-040 ? and 109-2634-F-002-041"],"award-info":[{"award-number":["109-2634-F-002-027- ,109-2634-F-002-040 ? and 109-2634-F-002-041"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,23]]},"DOI":"10.1145\/3439133.3439142","type":"proceedings-article","created":{"date-parts":[[2021,3,7]],"date-time":"2021-03-07T01:52:03Z","timestamp":1615081923000},"page":"16-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Modular AR Framework for Vision-Language Tasks"],"prefix":"10.1145","author":[{"given":"Robin","family":"Fischer","sequence":"first","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tzu-Hsuan","family":"Weng","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-Chen","family":"Fu","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,3,6]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","author":"Goyal Y.","year":"2016","unstructured":"Goyal , Y. , Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering . 2016 . arXiv:1612.00837. Goyal, Y., Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. 2016. arXiv:1612.00837."},{"key":"e_1_3_2_2_2_1","unstructured":"Seeing-AI App. 01.09.2020; Available from: https:\/\/www.microsoft.com\/en-us\/ai\/seeing-ai.  Seeing-AI App. 01.09.2020; Available from: https:\/\/www.microsoft.com\/en-us\/ai\/seeing-ai."},{"key":"e_1_3_2_2_3_1","volume-title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","author":"Gurari D.","year":"2018","unstructured":"Gurari , D. , VizWiz Grand Challenge: Answering Visual Questions from Blind People . 2018 . arXiv:1802.08218. Gurari, D., VizWiz Grand Challenge: Answering Visual Questions from Blind People. 2018. arXiv:1802.08218."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"e_1_3_2_2_5_1","unstructured":"Microservice Architecture. 01.09.2020; Available from: https:\/\/en.wikipedia.org\/wiki\/Microservices.  Microservice Architecture. 01.09.2020; Available from: https:\/\/en.wikipedia.org\/wiki\/Microservices."},{"key":"e_1_3_2_2_6_1","unstructured":"Unity Engine. 01.09.2020; Available from: https:\/\/en.wikipedia.org\/wiki\/Unity_(game_engine).  Unity Engine. 01.09.2020; Available from: https:\/\/en.wikipedia.org\/wiki\/Unity_(game_engine)."},{"key":"e_1_3_2_2_7_1","unstructured":"MQTT Network Protocol. 01.09.2020; Available from: https:\/\/mqtt.org\/.  MQTT Network Protocol. 01.09.2020; Available from: https:\/\/mqtt.org\/."},{"key":"e_1_3_2_2_8_1","volume-title":"UNITER: UNiversal Image-TExt Representation Learning","author":"Chen Y.-C.","year":"2019","unstructured":"Chen , Y.-C. , UNITER: UNiversal Image-TExt Representation Learning . 2019 . arXiv:1909.11740. Chen, Y.-C., UNITER: UNiversal Image-TExt Representation Learning. 2019. arXiv:1909.11740."},{"key":"e_1_3_2_2_9_1","unstructured":"Google Cloud Speech-API. 01.09.2020; Available from: https:\/\/cloud.google.com\/speech-to-text.  Google Cloud Speech-API. 01.09.2020; Available from: https:\/\/cloud.google.com\/speech-to-text."},{"key":"e_1_3_2_2_10_1","unstructured":"Magic Leap 1 Hardware Specifications. 01.09.2020; Available from: https:\/\/www.magicleap.com\/en-us\/magic-leap-1.  Magic Leap 1 Hardware Specifications. 01.09.2020; Available from: https:\/\/www.magicleap.com\/en-us\/magic-leap-1."},{"key":"e_1_3_2_2_11_1","unstructured":"Color Blindness Simulator. 01.09.2020; Available from: https:\/\/www.color-blindness.com\/coblis-color-blindness-simulator\/.  Color Blindness Simulator. 01.09.2020; Available from: https:\/\/www.color-blindness.com\/coblis-color-blindness-simulator\/."},{"key":"e_1_3_2_2_12_1","volume-title":"Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences","author":"Zhang Z.","year":"2020","unstructured":"Zhang , Z. , Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences . 2020 . arXiv:2001.06891. Zhang, Z., Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences. 2020. arXiv:2001.06891."},{"key":"e_1_3_2_2_13_1","volume-title":"S. and J. St-Pierre. Interfacing with Global Collective Intelligence Using Virtual Assistants. in 2018 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct).","author":"C\u00f6t\u00e9","year":"2018","unstructured":"C\u00f6t\u00e9 , S. and J. St-Pierre. Interfacing with Global Collective Intelligence Using Virtual Assistants. in 2018 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct). 2018 . C\u00f6t\u00e9, S. and J. St-Pierre. Interfacing with Global Collective Intelligence Using Virtual Assistants. in 2018 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct). 2018."}],"event":{"name":"AIVR2020: 2020 4th International Conference on Artificial Intelligence and Virtual Reality","acronym":"AIVR2020","location":"Kumamoto Japan"},"container-title":["2020 4th International Conference on Artificial Intelligence and Virtual Reality"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3439133.3439142","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3439133.3439142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:20Z","timestamp":1750193240000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3439133.3439142"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,23]]},"references-count":13,"alternative-id":["10.1145\/3439133.3439142","10.1145\/3439133"],"URL":"https:\/\/doi.org\/10.1145\/3439133.3439142","relation":{},"subject":[],"published":{"date-parts":[[2020,10,23]]},"assertion":[{"value":"2021-03-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}