Introduction
Welcome to the competition, again :D. This competition is for SC Students in Computer Vision course at FCIS. The goal of the competition is to build deep learning models that can recognize the action of the video.
Action recognition task involves the identification of different actions from video clips (a
sequence of 2D frames) where the action may or may not be performed throughout the
entire duration of the video. This seems like a natural extension of image classification
tasks to multiple frames and then aggregating the predictions from each frame.