Text-to-3D generation from a single-view image is a popular but challeng...
Text-Pedestrian Image Retrieval aims to use the text describing pedestri...
For multi-modal magnetic resonance (MR) brain tumor image segmentation,
...
Egocentric action recognition is gaining significant attention in the fi...
In visible-infrared video person re-identification (re-ID), extracting
f...
Graph Neural Networks (GNNs) tend to suffer from high computation costs ...
Domain adaptation aims to generalize a model from a source domain to tac...
Cross-modality person re-identification is a challenging problem which
r...
An increasing number of well-trained deep networks have been released on...
In this paper, we investigate a novel deep-model reusing task. Our goal ...
Two-stream architecture have shown strong performance in video classific...
Recently, manifold regularized semi-supervised learning (MRSSL) received...
Discriminative features are critical for machine learning applications. ...
The ever-growing popularity of Kinect and inertial sensors has prompted
...