Generating videos with scene dynamics
We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e.g. action classification) and video generation tasks (e.g. future prediction). We propose a generative adversarial network for video with a spatio-temporal convolutional...
Main Authors: | Vondrick, Carl, Pirsiavash, Hamed, Torralba, Antonio |
---|---|
Drugi avtorji: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
Format: | Article |
Jezik: | English |
Izdano: |
2020
|
Online dostop: | https://hdl.handle.net/1721.1/124545 |
Podobne knjige/članki
-
Anticipating Visual Representations from Unlabeled Video
od: Vondrick, Carl, et al.
Izdano: (2018) -
Cross-Modal Scene Networks
od: Aytar, Yusuf, et al.
Izdano: (2021) -
Cross-Modal Scene Networks
od: Aytar, Yusuf, et al.
Izdano: (2022) -
Assessing the Quality of Actions
od: Pirsiavash, Hamed, et al.
Izdano: (2014) -
Predicting Motivations of Actions by Leveraging Text
od: Pirsiavash, Hamed, et al.
Izdano: (2018)