Generic Event Boundary Detection

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

CC BY

Source arXiv

Computer Vision

Generic Event Boundary Detection

Generic Event Boundary Detection: A Benchmark for Event Segmentation

This paper presents a novel task together with a new benchmark for detecting generic, taxonomy-free event boundaries that segment a whole video into chunks.

With our novel annotation guideline which addresses the complexities of taxonomy-free event boundary annotation, we introduce the task of genericevent boundary detection (gebd) and the new benchmark kinetics-gebd.

We identify and extensively explore important design factors for gebd models on the tapos dataset and our kinetics-gebd while achieving competitive performance and suggesting future work.

Authors

Mike Zheng Shou, Deepti Ghadiyaram, Weiyao Wang, Matt Feiszli

◐ Recommended Follows

◐ Latest Activity