2023 · 12 citations · 41 references
ComputingComputer ScienceComputer VisionMachine VisionNatural Language ProcessingDeep LearningLanguage ModelingNatural Language UnderstandingQuestion AnsweringScene UnderstandingVisual Question AnsweringCaptioningEncoder-decoder ArchitecturesImage CaptioningMultimodal Scene UnderstandingScene Text Recognition
Visual Question Answering (VQA) and Image Captioning (CAP), which are among the most popular vision-language tasks, have analogous scene-text versions that require reasoning from the text in the image. Despite their obvious resemblance, the two are treated independently and, as we show, yield task-specific methods that can either see or read, but not both. In this work, we conduct an in-depth analysis of this phenomenon and propose UniTNT, a Unified Text-Non-Text approach, which grants existing multimodal architectures scene-text understanding capabilities. Specifically, we treat scene-text information as an additional modality, fusing it with any pretrained encoder-decoder-based architecture via designated modules. Thorough experiments reveal that UniTNT leads to the first single model that successfully handles both task types. Moreover, we show that scene-text understanding capabilities can boost vision-language models’ performance on general VQA and CAP by up to 2.69% and 0.6 CIDEr, respectively.
41
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
VQA: Visual Question Answering
Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu et al. · 2015 · 4.3K citations
Microsoft COCO: Common Objects in Context
arXiv (Cornell University) · 2014 · 2.4K citations · Full text