
Efficient Video Object Segmentation with Compressed Video
We propose an efficient inference framework for semisupervised video ob...
read it

Objectiveaware Traffic Simulation via Inverse Reinforcement Learning
Traffic simulators act as an essential component in the operating and pl...
read it

ROSEFusion: Random Optimization for Online Dense Reconstruction under Fast Camera Motion
Online reconstruction based on RGBD sequences has thus far been restrai...
read it

Couplings for Multinomial Hamiltonian Monte Carlo
Hamiltonian Monte Carlo (HMC) is a popular sampling method in Bayesian i...
read it

Potential Convolution: Embedding Point Clouds into Potential Fields
Recently, various convolutions based on continuous or discrete kernels f...
read it

Learning FineGrained Segmentation of 3D Shapes without Part Labels
Learningbased 3D shape segmentation is usually formulated as a semantic...
read it

StablePose: Learning 6D Object Poses from Geometrically Stable Patches
We introduce the concept of geometric stability to the problem of 6D obj...
read it

Hausdorff Point Convolution with Geometric Priors
Without a shapeaware response, it is hard to characterize the 3D geomet...
read it

Autonomous Outdoor Scanning via Online Topological and Geometric Path Optimization
Autonomous 3D acquisition of outdoor environments poses special challeng...
read it

Improving the Reconstruction of Disentangled Representation Learners via MultiStage Modelling
Current autoencoderbased disentangled representation learning methods a...
read it

Towards TargetDriven Visual Navigation in Indoor Scenes via Generative Imitation Learning
We present a targetdriven navigation system to improve mapless visual n...
read it

WarpCore: A Library for fast Hash Tables on GPUs
Hash tables are ubiquitous. Properties such as an amortized constant tim...
read it

SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from SingleView RGBD Images
We study the problem of symmetry detection of 3D shapes from singleview...
read it

Online 3D Bin Packing with Constrained Deep Reinforcement Learning
We solve a challenging yet practically useful variant of 3D Bin Packing ...
read it

AReLU: Attentionbased Rectified Linear Unit
Elementwise activation functions play a critical role in deep neural ne...
read it

Telescoping DensityRatio Estimation
Densityratio estimation via classification is a cornerstone of unsuperv...
read it

MLCVNet: MultiLevel Context VoteNet for 3D Object Detection
In this paper, we address the 3D object detection task by capturing mult...
read it

FusionAware Point Convolution for Online Semantic 3D Scene Segmentation
Online semantic 3D segmentation in company with realtime RGBD reconstr...
read it

Learning in the Frequency Domain
Deep neural networks have achieved remarkable success in computer vision...
read it

DynamicPPL: Stanlike Speed for Dynamic Probabilistic Models
We present the preliminary highlevel design and features of DynamicPPL....
read it

Deep Differentiable Grasp Planner for HighDOF Grippers
We present an endtoend algorithm for training deep neural networks to ...
read it

Learning Canonical Shape Space for CategoryLevel 6D Object Pose and Size Estimation
We present a novel approach to categorylevel 6D object pose and size es...
read it

TemperatureAware Virtual Data Center Embedding to Avoid Hot Spots in Data Centers
Virtual Data Center (VDC) embedding has drawn significant attention rece...
read it

Constructing the FGraph with a Symmetric Constraint for Subspace Clustering
Based on further studying the lowrank subspace clustering (LRSC) and L2...
read it

Reinforcement Learning based Visual Navigation with InformationTheoretic Regularization
We present a targetdriven navigation approach for improving the crosst...
read it

Decoupling Features and Coordinates for Fewshot RGB Relocalization
Crossscene model adaption is a crucial feature for camera relocalizatio...
read it

Rescan: Inductive Instance Segmentation for Indoor RGBD Scans
In depthsensing applications ranging from home robotics to AR/VR, it wi...
read it

New Formulation of MixedInteger Conic Programming for Globally Optimal Grasp Planning
We present a twolevel branchandbound (BB) algorithm to compute the gl...
read it

Globally Optimal Grasp Planning using a TwoStage BranchAndBound Algorithm
We present the first algorithm to compute the globally optimal gripper p...
read it

Building change detection based on multiscale filtering and grid partition
Building change detection is of great significance in high resolution re...
read it

Multiple instance dense connected convolution neural network for aerial image scene classification
With the development of deep learning, many stateoftheart natural ima...
read it

Active Scene Understanding via Online Semantic Reconstruction
We propose a novel approach to robotoperated active understanding of un...
read it

Visual Navigation by Generating Next Expected Observations
We propose a novel approach to visual navigation in unknown environments...
read it

Learning Part Generation and Assembly for Structureaware Shape Synthesis
Learning deep generative models for 3D shape synthesis is largely limite...
read it

Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference
Extracellular recordings using modern, dense probes provide detailed foo...
read it

Globally Optimal Joint Search of Topology and Trajectory for Planar Linkages
We present a method to find globally optimal topology and trajectory joi...
read it

Learning Phase Competition for Traffic Signal Control
Increasingly available city data and advanced learning techniques have e...
read it

Diagnosing Reinforcement Learning for Traffic Signal Control
With the increasing availability of traffic data and advance of deep rei...
read it

CoLight: Learning Networklevel Cooperation for Traffic Signal Control
Cooperation is critical in multiagent reinforcement learning (MARL). In...
read it

Spatiotemporal CNN for Video Object Segmentation
In this paper, we present a unified, endtoend trainable spatiotemporal...
read it

CoSegNet: Deep CoSegmentation of 3D Shapes with Group Consistency Loss
We introduce CoSegNet, a deep neural network architecture for cosegment...
read it

Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes
For the task of mobility analysis of 3D shapes, we propose joint analysi...
read it

Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction
Indoor scenes exhibit rich hierarchical structure in 3D object layouts. ...
read it

PartNet: A Recursive Part Decomposition Network for Finegrained and Hierarchical Shape Segmentation
Deep learning approaches to 3D shape segmentation are typically formulat...
read it

Generating Grasp Poses for a HighDOF Gripper Using Neural Networks
We present a learningbased method to represent grasp poses of a highDO...
read it

SCORES: Shape Composition with Recursive Substructure Priors
We introduce SCORES, a recursive neural network for shape composition. O...
read it

Learning to Group and Label FineGrained Shape Components
A majority of stock 3D models in modern shape repositories are assembled...
read it

VERAM: ViewEnhanced Recurrent Attention Model for 3D Shape Classification
Multiview deep neural network is perhaps the most successful approach i...
read it

Triangle Lasso for Simultaneous Clustering and Optimization in Graph Datasets
Recently, network lasso has drawn many attentions due to its remarkable ...
read it

Learning Discriminative 3D Shape Representations by View Discerning Networks
In viewbased 3D shape recognition, extracting discriminative visual rep...
read it
Kai Xu
is this you? claim profile
Associate Professor at School of Computer Science, National University of Defense Technology (NUDT). Starting July 2017, he is visiting Princeton University as a Research Scientist. He earned his Ph.D in computer science in 2011 from NUDT.