Large-scale Video Classification guided by Batch Normalized LSTM Translator

07/13/2017
by   Jae Hyeon Yoo, et al.
0

Youtube-8M dataset enhances the development of large-scale video recognition technology as ImageNet dataset has encouraged image classification, recognition and detection of artificial intelligence fields. For this large video dataset, it is a challenging task to classify a huge amount of multi-labels. By change of perspective, we propose a novel method by regarding labels as words. In details, we describe online learning approaches to multi-label video classification that are guided by deep recurrent neural networks for video to sentence translator. We designed the translator based on LSTMs and found out that a stochastic gating before the input of each LSTM cell can help us to design the structural details. In addition, we adopted batch normalizations into our models to improve our LSTM models. Since our models are feature extractors, they can be used with other classifiers. Finally we report improved validation results of our models on large-scale Youtube-8M datasets and discussions for the further improvement.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/24/2017

Encoding Video and Label Priors for Multi-label Video Classification on YouTube-8M dataset

YouTube-8M is the largest video dataset for multi-label video classifica...
research
09/27/2016

YouTube-8M: A Large-Scale Video Classification Benchmark

Many recent advancements in Computer Vision are attributed to large data...
research
06/14/2017

Large-Scale YouTube-8M Video Understanding with Deep Neural Networks

Video classification problem has been studied many years. The success of...
research
07/05/2017

Video Representation Learning and Latent Concept Mining for Large-scale Multi-label Video Classification

We report on CMU Informedia Lab's system used in Google's YouTube 8 Mill...
research
06/26/2017

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

Large-scale datasets have played a significant role in progress of neura...
research
08/27/2018

Approach for Video Classification with Multi-label on YouTube-8M Dataset

Video traffic is increasing at a considerable rate due to the spread of ...
research
06/15/2017

Hierarchical Label Inference for Video Classification

Videos are a rich source of high-dimensional structured data, with a wid...

Please sign up or login with your details

Forgot password? Click here to reset