Video Contents Understanding using Deep Neural Networks

by   Mohammadhossein Toutiaee, et al.
University of Georgia

We propose a novel application of Transfer Learning to classify video-frame sequences over multiple classes. This is a pre-weighted model that does not require to train a fresh CNN. This representation is achieved with the advent of "deep neural network" (DNN), which is being studied these days by many researchers. We utilize the classical approaches for video classification task using object detection techniques for comparison, such as "Google Video Intelligence API" and this study will run experiments as to how those architectures would perform in foggy or rainy weather conditions. Experimental evaluation on video collections shows that the new proposed classifier achieves superior performance over existing solutions.


page 2

page 3


Fusarium Damaged Kernels Detection Using Transfer Learning on Deep Neural Network Architecture

The present work shows the application of transfer learning for a pre-tr...

Handcrafted vs Deep Learning Classification for Scalable Video QoE Modeling

Mobile video traffic is dominant in cellular and enterprise wireless net...

Scalable Video Coding for Humans and Machines

Video content is watched not only by humans, but increasingly also by ma...

InSphereNet: a Concise Representation and Classification Method for 3D Object

In this paper, we present an InSphereNet method for the problem of 3D ob...

Video Monitoring Queries

Recent advances in video processing utilizing deep learning primitives a...

Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks

In this paper, we study the challenging problem of categorizing videos a...

Please sign up or login with your details

Forgot password? Click here to reset