Relation-aware subgraph embedding is promising for predicting
multi-rela...
Goal-conditioned hierarchical reinforcement learning (GCHRL) decomposes
...
Many scenes in real life can be abstracted to the sparse reward visual
s...
Self-supervised deep learning-based 3D scene understanding methods can
o...
Self-supervised learning of depth and ego-motion from unlabeled monocula...
Metric learning is a widely used method for few shot learning in which t...
The performances of GNNs for representation learning on the graph-struct...
Heterogeneous graph is a kind of data structure widely existing in real ...
Most previous few-shot learning algorithms are based on meta-training wi...
In this paper, we propose a more refined video segment based Mobile Edge...
More and more scholars focus on mobile edge computing (MEC) technology,
...
Unsupervised learning based depth estimation methods have received more ...
3D object detection is one of the most important tasks in 3D vision
perc...
Object tracking has been studied for decades, but most of the existing w...
Due to better video quality and higher frame rate, the performance of
mu...
For many real applications, it is equally important to detect objects
ac...