all AI news
Hypergraph Transformer for Skeleton-based Action Recognition. (arXiv:2211.09590v1 [cs.CV])
Nov. 18, 2022, 2:14 a.m. | Yuxuan Zhou, Chao Li, Zhi-Qi Cheng, Yifeng Geng, Xuansong Xie, Margret Keuper
cs.CV updates on arXiv.org arxiv.org
Skeleton-based action recognition aims to predict human actions given human
joint coordinates with skeletal interconnections. To model such off-grid data
points and their co-occurrences, Transformer-based formulations would be a
natural choice. However, Transformers still lag behind state-of-the-art methods
using graph convolutional networks (GCNs). Transformers assume that the input
is permutation-invariant and homogeneous (partially alleviated by positional
encoding), which ignores an important characteristic of skeleton data, i.e.,
bone connectivity. Furthermore, each type of body joint has a clear physical
meaning in …
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Codec Avatars Research Engineer
@ Meta | Pittsburgh, PA