Convolutional Architecture Exploration for Action Recognition and Image Classification

TL;DR

This paper explores convolutional neural network architectures and hyperparameters for effective action recognition and image classification using the UCF Sports Action dataset, focusing on feature extraction performance.

Contribution

It investigates architecture and hyperparameter choices for static video analysis and image classification, comparing caffe with overfeat.

Findings

Caffe outperforms overfeat in feature extraction.

Optimal architecture choices improve action recognition accuracy.

Hyperparameter tuning is crucial for effective static analysis.

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 effective static analysis of action in videos and classification over a variety of image datasets.