Multiple adverse weather conditions adaptation for object detection via causal intervention

H Zhang, L **ao, X Cao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Most state-of-the-art object detection methods have achieved impressive perfomrace on
several public benchmarks, which are trained with high definition images. However, existing …

Beyond vqa: Generating multi-word answers and rationales to visual questions

R Dua, SS Kancheti… - Proceedings of the …, 2021 - openaccess.thecvf.com
Abstract Visual Question Answering is a multi-modal task that aims to measure high-level
visual understanding. Contemporary VQA models are restrictive in the sense that answers …