CapERA: Captioning Events in Aerial Videos

Multi Target Tracking on Aerial Videos

In this paper we propose a new method to detect and track multiple moving targets on image sequences recorded by Unmanned Aerial Vehicles (UAVs). Our approach focuses on challenging urban scenarios, where several object are simultaneously moving in various directions, and we must expect frequent occlusions caused by other moving vehicles or static scene objects such as buildings and bridges. In...

The Effects of Captioning Videos on Academic Achievement and Motivation: Reconsideration of Redundancy Principle in Instructional Videos

The purpose of the present study was to investigate the effect of captioned vs. non-captioned instructional videos on the motivation and achievement. To this end, a pre-test and post-test experimental design was used on 109 sophomores from a Turkish state university. Videos with and without captions of the unit in question were prepared by the lecturer of the course “Graphics and Animation in E...

Decoding Hazardous Events in Driving Videos

Decoding the human brain state with BCI methods can be seen as a building block for humanmachine interaction, providing a noisy but objective, low-latency information channel including human reactions to the environment. Specifically in the context of autonomous driving, human judgement is relevant in high-level scene understanding. Despite advances in computer vision and scene understanding, i...

Angry Crowds: Detecting Violent Events in Videos

Automatic Recognition of Unpredictable Events in Videos

First we describe what we mean mder “‘predictability”’ of frames in an image s&am. If f~~ames are predictable, they are not as important as the onus that are unpredictable. We will rank these frames lower, since they can be inferred them from the previous flG!lnles. For aample, imagine the following situation. A person enters a camera view field, walks from left to right in front of the camera,...