TY - GEN
T1 - Fusion of detected objects in text for visual question answering
AU - Alberti, Chris
AU - Ling, Jeffrey
AU - Collins, Michael
AU - Reitter, David
N1 - Publisher Copyright:
© 2019 Association for Computational Linguistics
PY - 2019
Y1 - 2019
N2 - To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language. The “Bounding Boxes in Text Transformer” (B2T2) also leverages referential information binding words to portions of the image in a single unified architecture. B2T2 is highly effective on the Visual Commonsense Reasoning benchmark1, achieving a new state-of-the-art with a 25% relative reduction in error rate compared to published baselines and obtaining the best performance to date on the public leaderboard (as of May 22, 2019). A detailed ablation analysis shows that the early integration of the visual features into the text analysis is key to the effectiveness of the new architecture. A reference implementation of our models is provided2.
AB - To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language. The “Bounding Boxes in Text Transformer” (B2T2) also leverages referential information binding words to portions of the image in a single unified architecture. B2T2 is highly effective on the Visual Commonsense Reasoning benchmark1, achieving a new state-of-the-art with a 25% relative reduction in error rate compared to published baselines and obtaining the best performance to date on the public leaderboard (as of May 22, 2019). A detailed ablation analysis shows that the early integration of the visual features into the text analysis is key to the effectiveness of the new architecture. A reference implementation of our models is provided2.
UR - http://www.scopus.com/inward/record.url?scp=85084304205&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084304205&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85084304205
T3 - EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference
SP - 2131
EP - 2140
BT - EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference
PB - Association for Computational Linguistics
T2 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019
Y2 - 3 November 2019 through 7 November 2019
ER -