We are releasing a dataset containing videos of both fluent and non-flue...
Point cloud has drawn more and more research attention as well as real-w...
In this paper, we propose a new deep learning-based method for estimatin...
The rapid emergence of airborne platforms and imaging sensors are enabli...
Understanding human behavior and activity facilitates advancement of num...
Scene flow depicts the dynamics of a 3D scene, which is critical for var...
Cross-modal retrieval aims to learn discriminative and modal-invariant
f...
Vision-based monocular human pose estimation, as one of the most fundame...
Most of the existing self-supervised feature learning methods for 3D dat...
As part of the development of an educational tool that can help students...
The deficiency of 3D segmentation labels is one of the main obstacles to...
The success of supervised learning requires large-scale ground truth lab...
We propose a semi-supervised learning approach for video classification,...
Accurate detection of pulmonary nodules with high sensitivity and specif...
Accurate detection of pulmonary nodules with high sensitivity and specif...
In this paper, we propose a 3D Convolutional Neural Network (3DCNN) base...
This paper presents a new design approach of wearable robots that tackle...
Large-scale labeled data are generally required to train deep neural net...
Lung segmentation in computerized tomography (CT) images is an important...
Deep neural network-based semantic segmentation generally requires
large...
We present a method to incrementally generate complete 2D or 3D scenes w...
In this paper, we address the challenging problem of spatial and tempora...
To alleviate the expensive cost of data collection and annotation, many
...
In this paper, a self-guiding multimodal LSTM (sg-LSTM) image captioning...