GraphVid: It Only Takes a Few Nodes to Understand a Video
This work addresses the problem of high computational costs in video understanding for researchers with limited resources, though it is incremental in its approach.
The paper tackles video understanding by representing videos as graphs of superpixels, which reduces computational requirements by 10-fold while achieving results comparable to state-of-the-art methods on datasets like Kinetics-400 and Charades.
We propose a concise representation of videos that encode perceptually meaningful features into graphs. With this representation, we aim to leverage the large amount of redundancies in videos and save computations. First, we construct superpixel-based graph representations of videos by considering superpixels as graph nodes and create spatial and temporal connections between adjacent superpixels. Then, we leverage Graph Convolutional Networks to process this representation and predict the desired output. As a result, we are able to train models with much fewer parameters, which translates into short training periods and a reduction in computation resource requirements. A comprehensive experimental study on the publicly available datasets Kinetics-400 and Charades shows that the proposed method is highly cost-effective and uses limited commodity hardware during training and inference. It reduces the computational requirements 10-fold while achieving results that are comparable to state-of-the-art methods. We believe that the proposed approach is a promising direction that could open the door to solving video understanding more efficiently and enable more resource limited users to thrive in this research field.