Paper entitled “VIDI: A Video Dataset of Incidents” is accepted for publication in IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP 2022) within “Drone Network for Post-Earthquake Search and Rescue” project by our partners at ITU.

In this paper, a video dataset — Video Dataset of Incidents, VIDI — that contains 4,534 video clips corresponding to 43 incident categories is presented. Each incident class has around 100 videos with a duration of ten seconds on average. To increase diversity, the videos have
been searched in several languages. To assess the performance of the recent state-of-the-art approaches, Vision Transformer and TimeSformer, as well as to explore the contribution of
video-based information for incident classification, benchmark experiments were performed on the VIDI and Incidents Dataset. VIDI will be made publicly available. Additional materials can be found at the following link: https://github.com/vididataset/VIDI