1. Taking a hint: Leveraging explanations to make vision and language models more grounded;Selvaraju,2019
2. Self-critical reasoning for robust visual question answering;Wu,2019
3. Rubi: Reducing unimodal biases for visual question answering;Cadene,2019
4. Counterfactual vqa: A cause-effect look at language bias;Niu,2021
5. Overcoming language priors in visual question answering with adversarial regularization;Ramakrishnan,2018