Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives

TL;DR

This survey reviews the current state of video-language understanding systems, focusing on model architecture, training, and data challenges, and compares their performance while discussing future research directions.

Contribution

It provides a comprehensive overview of methods addressing key challenges in video-language understanding from multiple perspectives.

Findings

Performance comparison among existing methods

Identification of key challenges in model design, training, and data

Discussion of promising future research directions

Abstract

Humans use multiple senses to comprehend the environment. Vision and language are two of the most vital senses since they allow us to easily communicate our thoughts and perceive the world around us. There has been a lot of interest in creating video-language understanding systems with human-like senses since a video-language pair can mimic both our linguistic medium and visual environment with temporal dynamics. In this survey, we review the key tasks of these systems and highlight the associated challenges. Based on the challenges, we summarize their methods from model architecture, model training, and data perspectives. We also conduct performance comparison among the methods, and discuss promising directions for future research.