Context information plays an indispensable role in the success of semant...
Most state-of-the-art 3D object detectors heavily rely on LiDAR sensors ...
We focus on Unsupervised Domain Adaptation (UDA) for the task of semanti...
We achieve 3D semantic scene labeling by exploring semantic relation bet...
State-of-the-art image captioning methods mostly focus on improving visu...
Person re-identification aims to identify whether pairs of images belong...
Typical methods for supervised sequence modeling are built upon the recu...
In this paper, we are interested in pose estimation of animals. Animals
...
We present a unified, efficient and effective framework for point-cloud ...
Continuous sign language recognition (SLR) aims to translate a signing
s...
We present a new two-stage 3D object detection framework, named
sparse-t...
Current image translation methods, albeit effective to produce high-qual...
In this paper, we are interested in generating an cartoon face of a pers...
Albeit intensively studied, false prediction and unclear boundaries are ...
Irregular scene text, which has complex layout in 2D space, is challengi...
Typical techniques for video captioning follow the encoder-decoder frame...
A 3D point cloud describes the real scene precisely and intuitively.To d...
We explore the importance of spatial contextual information in human pos...
We present a novel 3D object detection framework, named IPOD, based on r...
In this paper, we propose a generative multi-column network for image
in...
Digital face manipulation has become a popular and fascinating way to to...
In single image deblurring, the "coarse-to-fine" scheme, i.e. gradually
...
Estimating correspondence between two images and extracting the foregrou...
We propose a principled convolutional neural pyramid (CNP) framework for...