Search Results for author: Bo-Han Fang

Found 2 papers, 0 papers with code

A Transformer-based Cross-modal Fusion Model with Adversarial Training for VQA Challenge 2021

no code implementations24 Jun 2021 Ke-Han Lu, Bo-Han Fang, Kuan-Yu Chen

In this paper, inspired by the successes of visionlanguage pre-trained models and the benefits from training with adversarial attacks, we present a novel transformerbased cross-modal fusion modeling by incorporating the both notions for VQA challenge 2021.

Visual Question Answering (VQA)

Cannot find the paper you are looking for? You can Submit a new open access paper.