# Towards Models that Can See and Read

Source: [Towards Models that Can See and Read](<https://www.sota2.com/research/paper/68fa6ed31e209131cea426ef>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:07:49.028Z

Authors: Roy Ganz, Oren Nuriel, Aviad Aberdam, Yair Kittenplon, Shai Mazor, Ron Litman

Published: 2023-01-18T09:36:41.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2301.07389>)

[PDF](<https://arxiv.org/pdf/2301.07389.pdf>)
