This technical report presents AutoGen, a new framework that enables
dev...
Visual feedback plays a crucial role in the process of amputation patien...
The prevalent use of benchmarks in current offline reinforcement learnin...
Motion prediction is crucial for autonomous driving systems to understan...
Offline reinforcement learning (RL) offers an appealing approach to
real...
Instance segmentation of point clouds is a crucial task in 3D field with...
Masked signal modeling has greatly advanced self-supervised pre-training...
Spatiotemporal (ST) data collected by sensors can be represented as
mult...
Most offline reinforcement learning (RL) methods suffer from the trade-o...
Semantic segmentation is still a challenging task for parsing diverse
co...
The second-order training methods can converge much faster than first-or...
Offline reinforcement learning (RL) methods can generally be categorized...
As a pioneering work exploring transformer architecture for 3D point clo...
Predicting multimodal future behavior of traffic participants is essenti...
In this report, we present the 1st place solution for motion prediction ...
Vascular segmentation extracts blood vessels from images and serves as t...
To boost a detector for single-frame 3D object detection, we present a n...
This paper presents a new approach to boost a single-modality (LiDAR) 3D...
Data augmentation with Mixup has been proven an effective method to
regu...
Dexterous prosthetic hands have better grasp performance than traditiona...
Deep learning approaches achieve prominent success in 3D semantic
segmen...
3D point cloud segmentation has made tremendous progress in recent years...
The training phases of Deep neural network (DNN) consumes enormous proce...
Vision transformer (ViT) has achieved competitive accuracy on a variety ...
3D point cloud understanding is an important component in autonomous dri...
Processing-in-memory (PIM) architectures have demonstrated great potenti...
Satellite networks are booming to provide high-speed and low latency Int...
Accelerating the neural network inference by FPGA has emerged as a popul...
Rapid progress in 3D semantic segmentation is inseparable from the advan...
Semantic segmentation has made tremendous progress in recent years. Howe...
This paper presents AppealNet, a novel edge/cloud collaborative architec...
Video action recognition (VAR) is a primary task of video understanding,...
We present Self-Ensembling Single-Stage object Detector (SE-SSD) for acc...
2D image representations are in regular grids and can be processed
effic...
Resistive Random-Access-Memory (ReRAM) crossbar is a promising technique...
3D object detection is receiving increasing attention from both industry...
Existing single-stage detectors for locating objects in point clouds oft...
Training semantic segmentation models requires a large amount of finely
...
Instance segmentation is an important task for scene understanding. Comp...
We present a novel and high-performance 3D object detection framework, n...
This paper describes a system that generates speaker-annotated transcrip...
This paper studies the measurement scheduling problem for a group of N m...
We achieve 3D semantic scene labeling by exploring semantic relation bet...
The high computation and memory storage of large deep neural networks (D...
Ubiquitous cyber-intrusions endanger the security of our devices constan...
Neural approximate computing gains enormous energy-efficiency at the cos...
Neural network based approximate computing is a universal architecture
p...
The training phases of Deep neural network (DNN) consume enormous proces...