j-min / Adversarial_Video_Summary

Unofficial PyTorch Implementation of SUM-GAN from "Unsupervised Video Summarization with Adversarial LSTM Networks" (CVPR 2017)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Adversarial_Video_Summary

PyTorch Implementation of SUM-GAN

Changes from Original paper

  • Video feature extractor
    • GoogleNet pool5 (1024) => ResNet-101 pool5 (2048)
    • Followed by linear projection to 500-dim
  • Stable GAN Training
    • Discriminator's learning rate: 1e-5 (Others: 1e-4)
    • Fix Discriminators' parameters for first 15 steps at every epoch.

Model figures

Model figure 1

Model figure 2

Model figure 3

Algorithm

Algorithm figure

About

Unofficial PyTorch Implementation of SUM-GAN from "Unsupervised Video Summarization with Adversarial LSTM Networks" (CVPR 2017)


Languages

Language:Python 100.0%