arxivst stuff from arxiv that you should probably bookmark

UC Merced Submission to the ActivityNet Challenge 2016

Abstract · Apr 11, 2017 19:11 ·

mbh features videos fc7 untrimmed c3d activitynet video scores cs-cv cs-mm

Arxiv Abstract

  • Yi Zhu
  • Shawn Newsam
  • Zaikun Xu

This notebook paper describes our system for the untrimmed classification task in the ActivityNet challenge 2016. We investigate multiple state-of-the-art approaches for action recognition in long, untrimmed videos. We exploit hand-crafted motion boundary histogram features as well feature activations from deep networks such as VGG16, GoogLeNet, and C3D. These features are separately fed to linear, one-versus-rest support vector machine classifiers to produce confidence scores for each action class. These predictions are then fused along with the softmax scores of the recent ultra-deep ResNet-101 using weighted averaging.

Read the paper (pdf) »