Business Process Management (BPM) is gaining increasing attention as it ...
Large pre-trained models, also known as foundation models (FMs), are tra...
Inverse path tracing has recently been applied to joint material and lig...
Over the past decade, the electric vehicle industry has experienced
unpr...
Most existing methods to detect backdoored machine learning (ML) models ...
In this paper, we present a simple yet surprisingly effective technique ...
An important goal in artificial intelligence is to create agents that ca...
With extensive studies on backdoor attack and detection, still fundament...
Neural network representation learning for spatial data is a common need...
Most indoor 3D scene reconstruction methods focus on recovering 3D geome...
Indoor scenes exhibit significant appearance variations due to myriad
in...
We present a method to edit complex indoor lighting from a single image ...
A common vision from science fiction is that robots will one day inhabit...
Narrative cartography is a discipline which studies the interwoven natur...
Almost all statements in knowledge bases have a temporal scope during wh...
A common need for artificial intelligence models in the broader geoscien...
Contrastive learning, which aims at minimizing the distance between posi...
In this paper, we provide a deep dive into the deployment of inference
a...
As an important part of Artificial Intelligence (AI), Question Answering...
Although deep face recognition benefits significantly from large-scale
t...
The loss function choice for any Support Vector Machine classifier has r...
A common vision from science fiction is that robots will one day inhabit...
Estimating relative camera poses from consecutive frames is a fundamenta...
The number of linear regions is one of the distinct properties of the ne...
Learning knowledge graph (KG) embeddings is an emerging technique for a
...
Many geoportals such as ArcGIS Online are established with the goal of
i...
Unsupervised text encoding models have recently fueled substantial progr...
Semi-supervised learning is a classification method which makes use of b...
3D objectness estimation, namely discovering semantic objects from 3D sc...
Link prediction is an important and frequently studied task that contrib...
Recently, several studies have explored methods for using KG embedding t...
We present MMDetection, an object detection toolbox that contains a rich...
In this paper, we propose a method for image-set classification based on...
As a long-standing problem in computer vision, face detection has attrac...
In recent year, tremendous strides have been made in face detection than...
Autonomous driving has attracted remarkable attention from both industry...
Large models are prevalent in modern machine learning scenarios, includi...
Current state-of-the-art object objectors are fine-tuned from the
off-th...
The formal theoretical analysis on channel correlations in both real ind...
With the growth of mobile devices and applications, the number of malici...
With the increasing popularity of Android smart phones in recent years, ...
The Receiver Operating Characteristic (ROC) surface is a generalization ...
Many machine learning models, including those with non-smooth regularize...
We study stochastic algorithms for solving non-convex optimization probl...
The ability to predict depth from a single image - using recent advances...
The problem of obtaining dense reconstruction of an object in a natural
...
Reconstructing 3D shapes from a sequence of images has long been a probl...
An emerging problem in computer vision is the reconstruction of 3D shape...
Matrix factorization is a popular approach to solving matrix estimation
...
The Lucas & Kanade (LK) algorithm is the method of choice for efficient ...