Cross-view Action Recognition via Contrastive View-invariant Representation

Kavli Affiliate: Dan Luo

| First 5 Authors: Yuexi Zhang, Dan Luo, Balaji Sundareshan, Octavia Camps, Mario Sznaier

| Summary:

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.

| Search Query: ArXiv Query: search_query=au:”Dan Luo”&id_list=&start=0&max_results=10

Read More