资源分类
》 资源 》论文》Unsupervised Learning of Disentangled Representations from Video

Unsupervised Learning of Disentangled Representations from Video

2020-02-12 | |  58 |   56 |   0

Abstract 

We present a new model D R N ET that learns disentangled image representations from video. Our approach leverages the temporal coherence of video and a novel adversarial loss to learn a representation that factorizes each frame into a stationary part and a temporally varying component. The disentangled representation can be used for a range of tasks. For example, applying a standard LSTM to the time-vary components enables prediction of future frames. We evaluate our approach on a range of synthetic and real videos, demonstrating the ability to coherently generate hundreds of steps into the future.

上一篇：Revisit Fuzzy Neural Network: Demystifying Batch Normalization and ReLU with Generalized Hamming Network

下一篇：Fader Networks: Manipulating Images by Sliding Attributes

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...