|   | 
Details
   web
Record
Author Lluis Gomez; Ali Furkan Biten; Ruben Tito; Andres Mafla; Marçal Rusiñol; Ernest Valveny; Dimosthenis Karatzas
Title Multimodal grid features and cell pointers for scene text visual question answering Type Journal Article
Year 2021 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 150 Issue Pages 242-249
Keywords
Abstract This paper presents a new model for the task of scene text visual question answering. In this task questions about a given image can only be answered by reading and understanding scene text. Current state of the art models for this task make use of a dual attention mechanism in which one attention module attends to visual features while the other attends to textual features. A possible issue with this is that it makes difficult for the model to reason jointly about both modalities. To fix this problem we propose a new model that is based on an single attention mechanism that attends to multi-modal features conditioned to the question. The output weights of this attention module over a grid of multi-modal spatial features are interpreted as the probability that a certain spatial location of the image contains the answer text to the given question. Our experiments demonstrate competitive performance in two standard datasets with a model that is faster than previous methods at inference time. Furthermore, we also provide a novel analysis of the ST-VQA dataset based on a human performance study. Supplementary material, code, and data is made available through this link.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes (up) DAG; 600.084; 600.121 Approved no
Call Number Admin @ si @ GBT2021 Serial 3620
Permanent link to this record