In spite of the rapidly evolving landscape of text-to-image generation, ...
Recent advancements in language models (LMs) have gained substantial
att...
Multi-object tracking (MOT) is a challenging vision task that aims to de...
Deep Neural Networks (DNNs) have been used to solve different day-to-day...
In the recent years, many software systems have adopted AI techniques,
e...
Future intelligent robots are expected to process multiple inputs
simult...
DL compiler's primary function is to translate DNN programs written in
h...
The goal of program synthesis, or code generation, is to generate execut...
Treatment planning is a critical component of the radiotherapy workflow,...
There is an emerging effort to combine the two popular technical paths, ...
Deep Learning (DL) models have been popular nowadays to execute differen...
Recent research in offline reinforcement learning (RL) has demonstrated ...
Despite much success in natural language processing (NLP), pre-trained
l...
Significant advancements have been made in developing parametric models ...
Subresultant is a powerful tool for developing various algorithms in com...
The research fields of parametric face models and 3D face reconstruction...
Numerical vector aggregation plays a crucial role in privacy-sensitive
a...
Due to Synthetic Aperture Radar (SAR) imaging characteristics, SAR vehic...
Recovering the physical attributes of an object's appearance from its im...
In recent years, deep learning has been widely used in SAR ATR and achie...
We propose the first framework to learn control policies for vision-base...
Learning discriminative features for effectively separating abnormal eve...
Recent success in Deep Reinforcement Learning (DRL) methods has shown th...
Transformer framework has been showing superior performances in visual o...
We revisit the estimation bias in policy gradients for the discounted
ep...
Whole-slide images (WSI) in computational pathology have high resolution...
Occluded person re-identification (ReID) is a challenging problem due to...
Dexterous robotic hands have the capability to interact with a wide vari...
This paper considers the massive random access problem in MIMO quasi-sta...
The recently proposed capability-based NLP testing allows model develope...
Today, an increasing number of Adaptive Deep Neural Networks (AdNNs) are...
Monocular depth estimation (MDE) in the self-supervised scenario has eme...
Neural Machine Translation (NMT) systems have received much recent atten...
Teaching a multi-fingered dexterous robot to grasp objects in the real w...
We study the adaption of soft actor-critic (SAC) from continuous action ...
A key challenge of continual reinforcement learning (CRL) in dynamic
env...
Knowledge distillation has emerged as a scalable and effective way for
p...
To improve the modeling resilience of silicon strong physical unclonable...
The pipeline of current robotic pick-and-place methods typically consist...
With the privatization deployment of DNNs on edge devices, the security ...
We introduce a new simulation benchmark "HandoverSim" for human-to-robot...
Transformer architecture has been showing its great strength in visual o...
Graph neural networks (GNNs) have been widely used in many real applicat...
Because of the increasing accuracy of Deep Neural Networks (DNNs) on
dif...
Human-robot handover is a fundamental yet challenging task in human-robo...
Neural image caption generation (NICG) models have received massive atte...
Existing neural reconstruction schemes such as Neural Radiance Field (Ne...
Reinforcement learning competitions advance the field by providing
appro...
Combined visual and force feedback play an essential role in contact-ric...
Some of the most exciting experiences that Metaverse promises to offer, ...