In this paper, we focus on the challenges of modeling deformable 3D obje...
Current vision language pretraining models are dominated by methods usin...
The goal of 3D pose transfer is to transfer the pose from the source mes...
Few-shot segmentation aims to learn a segmentation model that can be
gen...
Instance segmentation on 3D point clouds has been attracting increasing
...
Natural language BERTs are trained with language corpus in a self-superv...
Data augmentation is an important technique to reduce overfitting and im...
Knowledge distillation is a promising learning paradigm for boosting the...
3D pose transfer is one of the most challenging 3D generation tasks. It ...
In this work, we address the challenging task of few-shot segmentation.
...
Recently deep learning has achieved significant progress on point cloud
...
Semantic segmentation on 3D point clouds is an important task for 3D sce...
Scene flow in 3D point clouds plays an important role in understanding
d...
Optical flow, which expresses pixel displacement, is widely used in many...
Over the past few years, state-of-the-art image segmentation algorithms ...
It is challenging to detect curve texts due to their irregular shapes an...
Recent progress in semantic segmentation is driven by deep Convolutional...
In this work, we propose a novel hybrid method for scene text detection
...
We propose a new approach to image segmentation, which exploits the
adva...
Recent works on deep conditional random fields (CRF) have set new record...
Conditional Random Rields (CRF) have been widely applied in image
segmen...
In this article, we tackle the problem of depth estimation from single
m...
We consider the problem of depth estimation from a single monocular imag...
Ensemble methods such as boosting combine multiple learners to obtain be...
Feature encoding with respect to an over-complete dictionary learned by
...