The reviewed record of science sign in
Pith

arxiv: 2305.01733 · v1 · pith:WREQS5KN · submitted 2023-05-02 · cs.CV

Cross-view Action Recognition via Contrastive View-invariant Representation

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:WREQS5KNrecord.jsonopen to challenge →

classification cs.CV
keywords actioncvarskeletonsdatantu-rgbrecognitionviewpointwhen
0
0 comments X
read the original abstract

Cross view action recognition (CVAR) seeks to recognize a human action when observed from a previously unseen viewpoint. This is a challenging problem since the appearance of an action changes significantly with the viewpoint. Applications of CVAR include surveillance and monitoring of assisted living facilities where is not practical or feasible to collect large amounts of training data when adding a new camera. We present a simple yet efficient CVAR framework to learn invariant features from either RGB videos, 3D skeleton data, or both. The proposed approach outperforms the current state-of-the-art achieving similar levels of performance across input modalities: 99.4% (RGB) and 99.9% (3D skeletons), 99.4% (RGB) and 99.9% (3D Skeletons), 97.3% (RGB), and 99.2% (3D skeletons), and 84.4%(RGB) for the N-UCLA, NTU-RGB+D 60, NTU-RGB+D 120, and UWA3DII datasets, respectively.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.