-
MS^2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition
In this paper, we address self-supervised representation learning from h...
read it
-
Fashion Meets Computer Vision: A Survey
Fashion is the way we present ourselves to the world and has become one ...
read it
-
Modality Compensation Network: Cross-Modal Adaptation for Action Recognition
With the prevalence of RGB-D cameras, multi-modal video data have become...
read it
-
Unsupervised Person Image Generation with Semantic Parsing Transformation
In this paper, we address unsupervised pose-guided person image generati...
read it
-
Temporal Bilinear Networks for Video Action Recognition
Temporal modeling in videos is a fundamental yet challenging problem in ...
read it
-
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding
Despite the fact that many 3D human activity benchmarks being proposed, ...
read it
-
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
Human action recognition is an important task in computer vision. Extrac...
read it

Sijie Song
is this you? claim profile