Deep Learning Methods for Efficient Large Scale Video Labeling

Abstract

We present a solution to "Google Cloud and YouTube-8M Video Understanding Challenge" that ranked 5th place. The proposed model is an ensemble of three model families, two frame level and one video level. The training was performed on augmented dataset, with cross validation.

7 pages, 5 tables, 1 figure

References in corpus (3)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• YouTube-8M: A Large-Scale Video Classification Benchmark
• Show and Tell: A Neural Image Caption Generator

Cited by in corpus (5)

• Learnable pooling with Context Gating for video classification
• BERT for Large-scale Video Segment Classification with Test-time Augmentation
• Building Compact and Robust Deep Neural Networks with Toeplitz Matrices
• Training compact deep learning models for video classification using circulant matrices
• Constrained-size Tensorflow Models for YouTube-8M Video Understanding Challenge