TitleConvolutional Architecture Exploration for Action Recognition and Image Classification
Publication TypeReport
Year of Publication2015
AuthorsTurner, JT, Aha, D, Smith, L, Gupta, KMoy
Abstract

Convolutional Architecture for Fast Feature Encoding (CAFFE) [11] is a software package for the training, classifying, and feature extraction of images. The UCF Sports Action dataset is a widely used machine learning dataset that has 200 videos taken in 720x480 resolution of 9 different sporting activities: diving, golf, swinging, kicking, lifting, horseback riding, running, skateboarding, swinging (various gymnastics), and walking. In this report we report on a caffe feature extraction pipeline of images taken from the videos of the UCF Sports Action dataset. A similar test was performed on overfeat, and results were inferior to caffe. This study is intended to explore the architecture and hyper parameters needed for eective static analysis of action in videos and classification over a variety of image datasets.

pdf: 
https://www.nrl.navy.mil/itd/aic/sites/www.nrl.navy.mil.itd.aic/files/pdfs/%28Turner%2B%202015%20TN%29%20Convolutional%20Architecture%20Exploration.pdf
NRL Publication Release Number: 
15-1231-1194