MMFT-BERT: Multimodal Fusion Transformer With BERT Encodings For Visual Question Answering | Awesome LLM Papers Add your paper to Awesome LLM Papers

MMFT-BERT: Multimodal Fusion Transformer With BERT Encodings For Visual Question Answering

Aisha Urooj Khan, Amir Mazaheri, Niels da Vitoria Lobo, Mubarak Shah . Findings of the Association for Computational Linguistics: EMNLP 2020 2020 – 43 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
ACL Datasets EMNLP Image Text Integration Interdisciplinary Approaches Model Architecture Question Answering Visual Contextualization Visual Question Answering

We present MMFT-BERT(MultiModal Fusion Transformer with BERT encodings), to solve Visual Question Answering (VQA) ensuring individual and combined processing of multiple input modalities. Our approach benefits from processing multimodal data (video and text) adopting the BERT encodings individually and using a novel transformer-based fusion method to fuse them together. Our method decomposes the different sources of modalities, into different BERT instances with similar architectures, but variable weights. This achieves SOTA results on the TVQA dataset. Additionally, we provide TVQA-Visual, an isolated diagnostic subset of TVQA, which strictly requires the knowledge of visual (V) modality based on a human annotator’s judgment. This set of questions helps us to study the model’s behavior and the challenges TVQA poses to prevent the achievement of super human performance. Extensive experiments show the effectiveness and superiority of our method.

Similar Work