Deep Learning Methods for Efficient Large Scale Video Labeling

06/14/2017

∙

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.

READ FULL TEXT

Deep Learning Methods for Efficient Large Scale Video Labeling

Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding

Learning to Localize Temporal Events in Large-scale Video Data

Cultivating DNN Diversity for Large Scale Video Labelling

Label Denoising with Large Ensembles of Heterogeneous Neural Networks

Non-local NetVLAD Encoding for Video Classification

An Effective Way to Improve YouTube-8M Classification Accuracy in Google Cloud Platform

BERT for Large-scale Video Segment Classification with Test-time Augmentation

Deep Learning Methods for Efficient Large Scale Video Labeling

Related Research

Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding

Learning to Localize Temporal Events in Large-scale Video Data

Cultivating DNN Diversity for Large Scale Video Labelling

Label Denoising with Large Ensembles of Heterogeneous Neural Networks

Non-local NetVLAD Encoding for Video Classification

An Effective Way to Improve YouTube-8M Classification Accuracy in Google Cloud Platform

BERT for Large-scale Video Segment Classification with Test-time Augmentation