Keywords: Video Synthesis, Vision and Language, Representation Learning
Abstract: Videos of actions are complex signals, containing rich compositional structure. Current video generation models are limited in their ability to generate such videos. To address this challenge, we introduce a generative model (AG2Vid) that can be conditioned on an Action Graph, a structure that naturally represents the dynamics of actions and interactions between objects. Our AG2Vid model disentangles appearance and position features, allowing for more accurate generation. AG2Vid is evaluated on the CATER and Something-Something datasets and outperforms other baselines. Finally, we show how Action Graphs can be used for generating novel compositions of actions.
One-sentence Summary: We introduce Action Graphs, a natural and convenient structure representing the dynamics of actions between objects over time. We show we can synthesize goal-oriented videos and generate novel compositions of unseen actions from it on two datasets.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Supplementary Material: zip
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 3 code implementations](https://www.catalyzex.com/paper/arxiv:2006.15327/code)
Reviewed Version (pdf): https://openreview.net/references/pdf?id=QPmWFhqQU6