Search Results for author: Maxat Alibayev

Found 2 papers, 0 papers with code

Developing Motion Code Embedding for Action Recognition in Videos

no code implementations10 Dec 2020 Maxat Alibayev, David Paulius, Yu Sun

In this work, we propose a motion embedding strategy known as motion codes, which is a vectorized representation of motions based on a manipulation's salient mechanical attributes.

Action Recognition In Videos

Estimating Motion Codes from Demonstration Videos

no code implementations31 Jul 2020 Maxat Alibayev, David Paulius, Yu Sun

A motion taxonomy can encode manipulations as a binary-encoded representation, which we refer to as motion codes.

Cannot find the paper you are looking for? You can Submit a new open access paper.