Vision and Language (VL) models have demonstrated remarkable zero-shot performance in
a variety of tasks. However, some aspects of complex language understanding still remain a …

Multimodal pre-training has propelled great advancement in vision-and-language research.
These large-scale pre-trained models, although successful, fatefully suffer from slow …

The widespread adoption of surveillance cameras in work environments has enabled the
direct and non-intrusive detection of productivity-related issues in the field of construction. In …

We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines
multilingual pre-training and multimodal pre-training into a unified framework via multitask …

Current state-of-the-art approaches to cross-modal retrieval process text and visual input
jointly, relying on Transformer-based architectures with cross-attention mechanisms that …

This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically,
we focus on multilingual text-to-video search and propose a Transformer-based model that …

Both image-caption pairs and translation pairs provide the means to learn deep
representations of and connections between languages. We use both types of pairs in …

One of the latest applications of Artificial Intelligence (AI) is to generate images from natural
language descriptions. These generators are now becoming available and achieve …

Despite the recent developments in the field of cross-modal retrieval, there has been less
research focusing on low-resource languages due to the lack of manually annotated …

Recently pre-trained multimodal models, such as CLIP, have shown exceptional capabilities
towards connecting images and natural language. The textual representations in English …