50 citations · 89 across the 15 of their papers we have counts for
15 papers
Monocular Depth Estimation via Neural Network with Learnable Algebraic Group and Ring Structures
Qianlei Wang, Kexun Chen, Shaolin Zhang +3
Monocular depth estimation (MDE) has witnessed remarkable progress driven by Convolutional Neural Networks and transformer-based architectures. However, these approaches typically…
Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers
Longkun Zou, Wanru Zhu, Ke Chen +4
Semantic pattern of an object point cloud is determined by its topological configuration of local geometries. Learning discriminative representations can be challenging due to larg…
ShuffleMix: Improving Representations via Channel-Wise Shuffle of Interpolated Hidden States
Kangjun Liu, Ke Chen, Lihua Guo +2
Mixup style data augmentation algorithms have been widely adopted in various tasks as implicit network regularization on representation learning to improve model generalization, wh…
Improving Deep Representation Learning via Auxiliary Learnable Target Coding
Kangjun Liu, Ke Chen, Kui Jia +1
Deep representation learning is a subfield of machine learning that focuses on learning meaningful and useful representations of data through deep neural networks. However, existin…
Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose
Yichen Zhang, Jiehong Lin, Ke Chen +3
Domain gap between synthetic and real data in visual regression (e.g. 6D pose estimation) is bridged in this paper via global feature alignment and local refinement on the coarse c…
Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization
Kangjun Liu, Ke Chen, Kui Jia
Fine-grained visual classification can be addressed by deep representation learning under supervision of manually pre-defined targets (e.g., one-hot or the Hadamard codes). Such ta…
BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimation
Zelin Xu, Yichen Zhang, Ke Chen +1
The challenges of learning a robust 6D pose function lie in 1) severe occlusion and 2) systematic noises in depth images. Inspired by the success of point-pair features, the goal o…
Fine-Grained Object Classification via Self-Supervised Pose Alignment
Xuhui Yang, Yaowei Wang, Ke Chen +2
Semantic patterns of fine-grained objects are determined by subtle appearance difference of local parts, which thus inspires a number of part-based methods. However, due to uncontr…
Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap
Yongwei Chen, Zihao Wang, Longkun Zou +2
Semantic analyses of object point clouds are largely driven by releasing of benchmarking datasets, including synthetic ones whose instances are sampled from object CAD models. Howe…
Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space
Jiehong Lin, Hongyang Li, Ke Chen +2
As a basic component of SE(3)-equivariant deep feature learning, steerable convolution has recently demonstrated its advantages for 3D semantic analysis. The advantages are, howeve…
Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds
Longkun Zou, Hui Tang, Ke Chen +1
The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to d…
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding
Shengheng Deng, Xun Xu, Chaozheng Wu +2
The ability to understand the ways to interact with objects from visual cues, a.k.a. visual affordance, is essential to vision-guided robotic research. This involves categorizing,…
Classification of Single-View Object Point Clouds
Zelin Xu, Ke Chen, Kangjun Liu +3
Object point cloud classification has drawn great research attention since the release of benchmarking datasets, such as the ModelNet and the ShapeNet. These benchmarks assume poin…
CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling
Jiehong Lin, Xian Shi, Yuan Gao +2
Point set is arguably the most direct approximation of an object or scene surface, yet its practical acquisition often suffers from the shortcoming of being noisy, sparse, and poss…
Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors
Lulu Tang, Ke Chen, Chaozheng Wu +3
Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manne…