1 code implementation • 3 Aug 2022 • Jun Wang, Mingfei Gao, Yuqian Hu, Ramprasaath R. Selvaraju, Chetan Ramaiah, ran Xu, Joseph F. JaJa, Larry S. Davis
To address this deficiency, we develop a new method to generate high-quality and diverse QA pairs by explicitly utilizing the existing rich text available in the scene context of each image.
1 code implementation • 20 May 2018 • Yu Jin, Joseph F. JaJa
In this work, we develop a new approach to learn graph-level representations, which includes a combination of unsupervised and supervised learning components.