• Publications
  • Influence
An End-to-End Baseline for Video Captioning
TLDR
We propose a simple end-to-end framework for video captioning that achieves state-of-the-art performance on standard benchmark datasets. Expand
  • 2
  • 1
End-to-End Video Captioning
TLDR
We propose to optimise both encoder and decoder simultaneously in an end-to-end fashion in a fine-tuning stage for video captioning. Expand
  • 3
  • PDF
Exploiting Synchronized Lyrics And Vocal Features For Music Emotion Detection
TLDR
This work shows a comparison between text-based and audio-based deep learning classification models using different techniques from Natural Language Processing and Music Information Retrieval domains. Expand
  • 1
  • PDF
On supporting e-learning in the field of resilience management with an open source authoring tool
AbstractAmong all the pedagogical and technological features that could be used with the aim of improving and making more effective online education, we have identified virtual and augmentedExpand