Completing a graph means inferring the missing nodes and edges from a
pa...
Corrupted labels and class imbalance are commonly encountered in practic...
Intention recognition is an important step to facilitate collaboration i...
One essential problem in skeleton-based action recognition is how to ext...
Generalizable person Re-Identification (ReID) has attracted growing atte...
In object detection, bounding box regression (BBR) is a crucial step tha...
One essential problem in skeleton-based action recognition is how to ext...
Current methods for skeleton-based human action recognition usually work...
Network structures in various backgrounds play important roles in social...
Slow Feature Analysis (SFA) extracts slowly varying features from a quic...
Current methods for skeleton-based human action recognition usually work...
Current methods for skeleton-based human action recognition usually work...
The Large-Scale Pedestrian Retrieval Competition (LSPRC) mainly focuses ...
In this work, we present Gumbel Graph Network, a model-free deep learnin...
Person Re-identification (ReID) is to identify the same person across
di...
Visual surveillance systems have become one of the largest data sources ...
State-of-the-art methods treat pedestrian attribute recognition as a
mul...
In this paper, we aim to improve the dataset foundation for pedestrian
a...