Humans exploit prior knowledge to describe images, and are able to adapt...
In this paper, we present a framework for Multilingual Scene Text Visual...
In this work, we propose Text-Degradation Invariant Auto Encoder (Text-D...
The task of image-text matching aims to map representations from differe...
Recent models for cross-modal retrieval have benefited from an increasin...
Scene text instances found in natural images carry explicit semantic
inf...
This paper presents a new model for the task of scene text visual questi...
Text contained in an image carries high-level semantics that can be expl...
This paper presents final results of ICDAR 2019 Scene Text Visual Questi...
Current visual question answering datasets do not consider the rich sema...
Textual information found in scene images provides high level semantic
i...