{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:20:05Z","timestamp":1781536805901,"version":"3.54.5"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"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":[[2022,8,29]]},"DOI":"10.1109\/ro-man53752.2022.9900586","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T15:57:30Z","timestamp":1664553450000},"page":"252-259","source":"Crossref","is-referenced-by-count":4,"title":["Improving Visual Question Answering by Leveraging Depth and Adapting Explainability"],"prefix":"10.1109","author":[{"given":"Amrita","family":"Panesar","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science,Stockholm,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fethiye Irmak","family":"Dogan","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science,Stockholm,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iolanda","family":"Leite","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning From the School of Electrical Engineering and Computer Science,Stockholm,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1515\/pjbr-2018-0009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref12","first-page":"1135","article-title":"why should i trust you?”: Explaining the predictions of any classifier","author":"ribeiro","year":"2016"},{"key":"ref13","first-page":"3145","article-title":"Learning important features through propagating activation differences","author":"shrikumar","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning - Volume 70"},{"key":"ref14","article-title":"Explainable agents and robots: Results from a systematic literature review","author":"anjomshoae","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673104"},{"key":"ref16","first-page":"461","article-title":"Asking follow-up clarifications to resolve ambiguities in human-robot conversation","author":"do?an","year":"2022","journal-title":"Proceedings of the 2022 ACM\/IEEE International Conference on Human-Robot Interaction"},{"key":"ref17","article-title":"Leveraging explainability for comprehending referring expressions in the real world","author":"do?an","year":"2021"},{"key":"ref18","first-page":"24","article-title":"Comparing error-handling strategies in human-human and human-robot dialogues","author":"gieselmann","year":"2006","journal-title":"Proc 8th Conf Nat Language Process (KONVENS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1209"},{"key":"ref4","article-title":"Using depth for improving referring expression comprehension in real-world environments","author":"do?an","year":"2021"},{"key":"ref27","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref6","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.09.198"},{"key":"ref7","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"li","year":"2019"},{"key":"ref2","article-title":"Are you talking to a machine? dataset and methods for multilingual image question answering","author":"gao","year":"2015"},{"key":"ref9","article-title":"Building trust in artificial intelligence, machine learning, and robotics","author":"siau","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref20","article-title":"Generating natural language explanations for visual question answering using scene graphs and visual attention","author":"ghosh","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00236"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref24","article-title":"spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing","author":"honnibal","year":"2017"},{"key":"ref23","article-title":"Question generation using transformers","author":"patil","year":"0"},{"key":"ref26","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"CVPR"},{"key":"ref25","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015"}],"event":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","location":"Napoli, Italy","start":{"date-parts":[[2022,8,29]]},"end":{"date-parts":[[2022,9,2]]}},"container-title":["2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9900506\/9900507\/09900586.pdf?arnumber=9900586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T19:04:42Z","timestamp":1667502282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9900586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/ro-man53752.2022.9900586","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]}}}