Segmenting actions by aligning video frames to learned prototypes

Video temporal action localization is the task of identifying and localizing specific actions or activities within a video stream. Instead of only classifying which actions occur in the video stream, we aim to detect when an action begins and ends. In this work, we focus on solving this task without any supervision. Existing unsupervised methods...

Evaluation of the SUM-GAN-AAE method for Video Summarization

Video summarization is a task which many researchers have tried to automate with deep learning methods. One of these methods is the SUM-GAN-AAE algorithm developed by Apostolidis et al. which is an unsupervised machine learning method evaluated in this study. The research aims at testing the algorithm's performance on the Breakfast dataset,...

PUNet: Temporal Action Proposal Generation with Positive Unlabeled Learning using Key Frame Annotations

A good action proposal method should generate proposals with high recall and high temporal overlap with groundtruth. The quality of the proposals relies on the labeled data available during training. Obtaining labeled data for untrimmed videos is a time consuming, expensive and error-prone task. The labels obtained are also subjective and the...

Tubelets: Unsupervised Action Proposals from Spatiotemporal Super-Voxels

This paper considers the problem of localizing actions in videos as sequences of bounding boxes. The objective is to generate action proposals that are likely to include the action of interest, ideally achieving high recall with few proposals. Our contributions are threefold. First, inspired by selective search for object proposals, we...