The YouTube-8M Kaggle Competition: Challenges and Methods
This work provides a review and guidelines for the YouTube-8M benchmark, potentially inspiring future research in video classification, but it is incremental as it builds on existing competition frameworks without introducing major innovations.
The authors tackled the YouTube-8M multi-label video classification challenge by analyzing frame-level data and proposing preliminary methods, achieving 10th place in the Kaggle competition within a month using strategies like multi-crop ensemble averaging.
We took part in the YouTube-8M Video Understanding Challenge hosted on Kaggle, and achieved the 10th place within less than one month's time. In this paper, we present an extensive analysis and solution to the underlying machine-learning problem based on frame-level data, where major challenges are identified and corresponding preliminary methods are proposed. It's noteworthy that, with merely the proposed strategies and uniformly-averaging multi-crop ensemble was it sufficient for us to reach our ranking. We also report the methods we believe to be promising but didn't have enough time to train to convergence. We hope this paper could serve, to some extent, as a review and guideline of the YouTube-8M multi-label video classification benchmark, inspiring future attempts and research.