2 citations · 2 across the 1 of their papers we have counts for
6 papers
Women Wearing Lipstick: Measuring the Bias Between an Object and Its Related Gender
Ahmed Sabir, Lluís Padró
In this paper, we investigate the impact of objects on gender bias in image captioning systems. Our results show that only gender-specific objects have a strong gender bias (e.g.,…
Belief Revision based Caption Re-ranker with Visual Semantic Information
Ahmed Sabir, Francesc Moreno-Noguer, Pranava Madhyastha +1
In this work, we focus on improving the captions generated by image-caption generation systems. We propose a novel re-ranking approach that leverages visual-semantic measures to id…
Textual Visual Semantic Dataset for Text Spotting
Ahmed Sabir, Francesc Moreno-Noguer, Lluís Padró
Text Spotting in the wild consists of detecting and recognizing text appearing in images (e.g. signboards, traffic signals or brands in clothing or objects). This is a challenging…
Semantic Relatedness Based Re-ranker for Text Spotting
Ahmed Sabir, Francesc Moreno-Noguer, Lluís Padró
Applications such as textual entailment, plagiarism detection or document clustering rely on the notion of semantic similarity, and are usually approached with dimension reduction…
Visual Re-ranking with Natural Language Understanding for Text Spotting
Ahmed Sabir, Francesc Moreno-Noguer, Lluís Padró
Many scene text recognition approaches are based on purely visual information and ignore the semantic relation between scene and text. In this paper, we tackle this problem from na…
Visual Semantic Re-ranker for Text Spotting
Ahmed Sabir, Francesc Moreno-Noguer, Lluís Padró
Many current state-of-the-art methods for text recognition are based on purely local information and ignore the semantic correlation between text and its surrounding visual context…