We consider the problem of lower bounding the error probability under th...
Consider a star network where each local node possesses a set of
distrib...
Identifying the direct causes or causal parents of a target variable is
...
We propose a novel framework for few-shot learning by leveraging large-s...
We present a new reproducible benchmark for evaluating robot manipulatio...
As a hot topic in recent years, the ability of pedestrians identificatio...
Learning causal structure among event types from discrete-time event
seq...
We introduce a novel robotic system for improving unseen object instance...
We propose a simple approach which combines the strengths of probabilist...
Learning under distribution shifts is a challenging task. One principled...
Sign language is the preferred method of communication of deaf or mute
p...
This work concerns developing communication- and computation-efficient
m...
Segmenting unseen objects is a critical task in many different domains. ...
This work concerns controlling the false discovery rate (FDR) in network...
It has become increasingly common nowadays to collect observations of fe...
3D reconstruction of novel categories based on few-shot learning is appe...
We introduce a neural implicit representation for grasps of objects from...
We introduce the Few-Shot Object Learning (FewSOL) dataset for object
re...
It is common practice to collect observations of feature and response pa...
Geometrical shape of airfoils, together with the corresponding flight
co...
We introduce a new simulation benchmark "HandoverSim" for human-to-robot...
The task of distribution generalization concerns making reliable predict...
The identification of pedestrians using radar micro-Doppler signatures h...
The Fixed-X knockoff filter is a flexible framework for variable selecti...
The Benjamini-Hochberg (BH) procedure is a celebrated method for multipl...
This paper proposes a category-level 6D object pose and shape estimation...
Deep neural networks based object detectors have shown great success in ...
The knockoff filter, recently developed by Barber and Candes, is an effe...
Inferring causal directions on discrete and categorical data is an impor...
6D grasping in cluttered scenes is a longstanding robotic manipulation
p...
Segmenting unseen object instances in cluttered environments is an impor...
We introduce DexYCB, a new dataset for capturing hand grasping of object...
Majority of the perception methods in robotics require depth information...
Learning high-level navigation behaviors has important implications: it
...
Causal inference using the restricted structural causal model framework
...
The quality of datasets is one of the key factors that affect the accura...
6D robotic grasping beyond top-down bin-picking scenarios is a challengi...
In this work, we propose information laundering, a novel framework for
e...
Segmenting unseen objects in cluttered scenes is an important skill that...
In order to function in unstructured environments, robots need the abili...
Current 6D object pose estimation methods usually require a 3D model for...
In robot manipulation, planning the motion of a robot manipulator to gra...
Visual topological navigation has been revitalized recently thanks to th...
To teach robots skills, it is crucial to obtain data with supervision. S...
In order to function in unstructured environments, robots need the abili...
Tracking 6D poses of objects from videos provides rich information to a ...
End-to-end learning for autonomous navigation has received substantial
a...
We consider the problem of providing dense segmentation masks for object...
Using synthetic data for training deep neural networks for robotic
manip...
Traffic for internet video streaming has been rapidly increasing and is
...