Handling language prior and compositional reasoning issues in Visual Question Answering system
Authors:
- Souvik ChowdhurySCSouvik Chowdhury
- Badal SoniBSBadal Soni
- 14 March 2025
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 635
Abstract
No abstract availableThis publication has 42 references indexed in Scilit:
- Prompting large language model with context and pre-answer for knowledge-based VQAPattern Recognition, 2024
- Multi-task hierarchical convolutional network for visual-semantic cross-modal retrievalPattern Recognition, 2024
- Overcoming language priors with self-contrastive learning for visual question answeringMultimedia Tools and Applications, 2022
- Evaluation of graph convolutional networks performance for visual question answering on reasoning datasetsMultimedia Tools and Applications, 2022
- Overcoming language priors in VQA via adding visual moduleNeural Computing and Applications, 2022
- Spatially Aware Multimodal Transformers for TextVQA2020
- Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering2017
- Modeling Relationships in Referential Expressions with Compositional Modular Networks2017
- Stacked Attention Networks for Image Question Answering2016
- Visual7W: Grounded Question Answering in Images2016