MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering
arXiv:2010.14095
Abstract
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.
arXiv commentAccepted at Findings of EMNLP 2020
References in corpus (16)
- Adam: A Method for Stochastic Optimization
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Distributed Representations of Words and Phrases and their Compositionality
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- VisualBERT: A Simple and Performant Baseline for Vision and Language
- VQA: Visual Question Answering
- VL-BERT: Pre-training of Generic Visual-Linguistic Representations
- ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
- LXMERT: Learning Cross-Modality Encoder Representations from Transformers
- A Focused Dynamic Attention Model for Visual Question Answering
- Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training
- CLEVRER: CoLlision Events for Video REpresentation and Reasoning
- DeepStory: Video Story QA by Deep Embedded Memory Networks
- TVQA+: Spatio-Temporal Grounding for Video Question Answering
- Visual Text Correction
- Gaining Extra Supervision via Multi-task learning for Multi-Modal Video Question Answering