In the era of large-scale language models, the substantial parameter siz...
This paper launches a new effort at modeling programmer attention by
pre...
Multivariate Time Series (MTS) forecasting involves modeling temporal
de...
State-of-the-art deep neural networks are trained with large amounts
(mi...
Multi-view 3D detection based on BEV (bird-eye-view) has recently achiev...
While language models are powerful and versatile, they often fail to add...
Decision-makers in GIS need to combine a series of spatial algorithms an...
The Detection Transformer (DETR) has revolutionized the design of CNN-ba...
Autonomous systems (AS) are systems that can adapt and change their beha...
Occlusion problem remains a key challenge in Optical Flow Estimation (OF...
In autonomous driving, an accurate understanding of environment, e.g., t...
Contrastive learning usually compares one positive anchor sample with lo...
Source-free Unsupervised Domain Adaptation (SF-UDA) aims to adapt a
well...
Semi-supervised learning has achieved notable success by leveraging very...
Label hierarchy is an important source of external knowledge that can en...
Contrastive learning is a powerful self-supervised learning method, but ...
Training machines to synthesize diverse handwritings is an intriguing ta...
Test-time adaptation (TTA) has shown to be effective at tackling distrib...
Recent works have revealed the superiority of feature-level fusion for
c...
Deep learning-based 3D object detectors have made significant progress i...
The power of Deep Neural Networks (DNNs) depends heavily on the training...
For many interdisciplinary fields, ML interpretations need to be consist...
We present an alternating least squares type numerical optimization sche...
Object detection for autonomous vehicles has received increasing attenti...
Understanding binary code is an essential but complex software engineeri...
Compiled software is delivered as executable binary code. Developers wri...
Deep learning (DL) has made significant progress in angle closure
classi...
Neural clone detection has attracted the attention of software engineeri...
Data explosion and an increase in model size drive the remarkable advanc...
Accurate tooth volume segmentation is a prerequisite for computer-aided
...
This paper studies a new, practical but challenging problem, called
Clas...
In this paper, we propose a genuine group-level contrastive visual
repre...
The inherent ambiguity in ground-truth annotations of 3D bounding boxes
...
Knowledge distillation(KD) is a widely-used technique to train compact m...
Modern code review is a critical and indispensable practice in a pull-re...
Test-time adaptation (TTA) seeks to tackle potential distribution shifts...
Typical vision backbones manipulate structured features. As a compromise...
We study the problem of efficient object detection of 3D LiDAR point clo...
Conventional deep models predict a test sample with a single forward
pro...
Unmanned aerial vehicles (UAVs), especially fixed-wing ones that withsta...
Car-following (CF) modeling, an essential component in simulating human ...
Attention mechanism plays a more and more important role in point cloud
...
We introduce an improvement to the feature pyramid network of standard o...
For autonomous driving, an essential task is to detect surrounding objec...
Deep long-tailed learning, one of the most challenging problems in visua...
Convolutional neural network has made remarkable achievements in
classif...
Opinion prediction is an emerging research area with diverse real-world
...
We develop lower bounds on communication in the memory hierarchy or betw...
Existing long-tailed recognition methods, aiming to train class-balance
...
In real-world applications, data often come in a growing manner, where t...