Being Negative but Constructively: Lessons Learnt from Creating Better
Visual Question Answering Datasets

Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets

24 April 2017

Wei-Lun Chao

Papers citing "Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets"

6 / 6 papers shown

Title
VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution S. Hall F. G. Abrantes Hanwen Zhu Grace A. Sodunke Aleksandar Shtedritski Hannah Rose Kirk CoGe 11 38 0 21 Jun 2023
All You May Need for VQA are Image Captions Soravit Changpinyo Doron Kukliansky Idan Szpektor Xi Chen Nan Ding Radu Soricut 27 70 0 04 May 2022
Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering Jihyung Kil Cheng Zhang D. Xuan Wei-Lun Chao 53 20 0 13 Sep 2021
An Empirical Study on Leveraging Scene Graphs for Visual Question Answering Cheng Zhang Wei-Lun Chao D. Xuan 21 50 0 28 Jul 2019
Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering Aishwarya Agrawal Dhruv Batra Devi Parikh Aniruddha Kembhavi OOD 33 572 0 01 Dec 2017
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding Akira Fukui Dong Huk Park Daylen Yang Anna Rohrbach Trevor Darrell Marcus Rohrbach 144 1,458 0 06 Jun 2016