Nowadays, modern recommender systems usually leverage textual and visual...
Textual data are commonly used as auxiliary information for modeling use...
Aiming to produce reinforcement learning (RL) policies that are
human-in...
Multimodal learning is a recent challenge that extends unimodal learning...
Word embedding is a modern distributed word representations approach wid...
We study a novel task, Video Question-Answer Generation (VQAG), for
chal...