Unsupervised Learning of Disentangled Representations from Video

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Denton, Remi, Birodkar, Vighnesh
Natura: Preprint
Pubblicazione: 2017
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913263392915456
author Denton, Remi
Birodkar, Vighnesh
author_facet Denton, Remi
Birodkar, Vighnesh
contents We present a new model DrNET 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.
format Preprint
id arxiv_https___arxiv_org_abs_1705_10915
institution arXiv
publishDate 2017
record_format arxiv
spellingShingle Unsupervised Learning of Disentangled Representations from Video
Denton, Remi
Birodkar, Vighnesh
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
We present a new model DrNET 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.
title Unsupervised Learning of Disentangled Representations from Video
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/1705.10915