The YouTube-8M Kaggle Competition: Challenges and Methods

Abstract

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.

accepted to CVPR'17 Workshop on YouTube-8M Large-Scale Video Understanding (oral presentation); code is at https://github.com/taufikxu/youtube on branches kunxu and zhs

References in corpus (3)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Layer Normalization
• A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition

Cited by in corpus (5)

• The importance of ensemble techniques for operational space weather forecasting
• Improving the convergence of SGD through adaptive batch sizes
• Statistical hypothesis testing versus machine-learning binary classification: distinctions and guidelines
• On the Insufficiency of the Large Margins Theory in Explaining the Performance of Ensemble Methods
• Deep Multimodal Learning: An Effective Method for Video Classification