Motion planning is the soul of robot decision making. Classical planning...
Completely randomized experiment is the gold standard for causal inferen...
Bokeh is widely used in photography to draw attention to the subject whi...
Layer compositing is one of the most popular image editing workflows amo...
This report presents a study on the emotional dialogue capability of Cha...
Developing lightweight Deep Convolutional Neural Networks (DCNNs) and Vi...
Data in real-world object detection often exhibits the long-tailed
distr...
Long-tail distribution is widely spread in real-world applications. Due ...
As a critical step to achieve human-like chatbots, empathetic response
g...
Bayesian Optimization (BO) is a common solution to search optimal
hyperp...
Regression adjustment is widely used for the analysis of randomized
expe...
Analysis of single-cell transcriptomics often relies on clustering cells...
Despite the rapid advance of unsupervised anomaly detection, existing me...
Few-shot counting aims to count objects of any class in an image given o...
Pre-training has marked numerous state of the arts in high-level compute...
Global spatial statistics, which are aggregated along entire spatial
dim...
Binary neural networks (BNNs) constrain weights and activations to +1 or...
Image denoising is one of the most critical problems in mobile photo
pro...
In this paper, we explore the role of Instance Normalization in low-leve...
The two-stage methods for instance segmentation, e.g. Mask R-CNN, have
a...
"Episodic Logic:Unscoped Logical Form" (EL-ULF) is a semantic representa...
Recently proposed decoupled training methods emerge as a dominant paradi...
Modern object detection methods can be divided into one-stage approaches...
In machine learning, observation features are measured in a metric space...
Peer influence and social contagion are key denominators in the adoption...
We present MMDetection, an object detection toolbox that contains a rich...
Grid R-CNN is a well-performed objection detection framework. It transfo...
Endoscopy is a routine imaging technique used for both diagnosis and
min...
With the rapid growth of renewable energy resources, the energy trading ...
Existing image inpainting methods typically fill holes by borrowing
info...
This paper proposes a novel object detection framework named Grid R-CNN,...
While machine learning approaches to visual emotion recognition offer gr...
Existing video prediction methods mainly rely on observing multiple
hist...
We present a novel deep learning based image inpainting system to comple...
Model pruning has become a useful technique that improves the computatio...
In this paper, we address referring expression comprehension: localizing...
Recent deep learning based approaches have shown promising results on im...
We present a scene parsing method that utilizes global context informati...
Universal style transfer aims to transfer arbitrary visual styles to con...
In this paper we are interested in the problem of image segmentation giv...
Recent progresses on deep discriminative and generative modeling have sh...
Compositing is one of the most common operations in photo editing. To
ge...
Recent advances in deep learning have shown exciting promise in filling ...