The bokeh effect is an artistic technique that blurs out-of-focus areas ...
Much research has been done on user-generated textual passwords.
Surpris...
The captivating realm of Minecraft has attracted substantial research
in...
Clothing segmentation and fine-grained attribute recognition are challen...
Distilling the structured information captured in feature maps has
contr...
In recent years, there has been an increased popularity in image and spe...
Peridynamic (PD) theory is significant and promising in engineering and
...
Task-agnostic knowledge distillation attempts to address the problem of
...
Automatic colorization of anime line drawing has attracted much attentio...
Software engineers working with the same programming language (PL) may s...
We present a novel bird's-eye-view (BEV) detector with perspective
super...
Transferring large amount of high resolution images over limited bandwid...
Diffusion-based text-to-image generation models like GLIDE and DALLE-2 h...
Recent cross-lingual cross-modal works attempt to extend Vision-Language...
Recent progress in diffusion models has revolutionized the popular techn...
Derivative-free prompt learning has emerged as a lightweight alternative...
Recent years have witnessed the rise and success of pre-training techniq...
Recent Vision-Language Pre-trained (VLP) models based on dual encoder ha...
Graph kernels are conventional methods for computing graph similarities....
Neural retrievers based on pre-trained language models (PLMs), such as
d...
The absorption, distribution, metabolism, excretion, and toxicity (ADMET...
Deep learning became the game changer for image retrieval soon after it ...
Conventional methods for the image-text generation tasks mainly tackle t...
Pre-trained language models have achieved state-of-the-art results in va...
Recently reinforcement learning (RL) has emerged as a promising approach...
While artificial neural networks (ANNs) have been widely adopted in mach...
Combining off-policy reinforcement learning methods with function
approx...
Pre-trained models have achieved state-of-the-art results in various Nat...
Maintaining the stability of the modern power grid is becoming increasin...
Pretrained language models (PLMs) such as BERT adopt a training paradigm...
Transformers are not suited for processing long document input due to it...
Recent studies have demonstrated that pre-trained cross-lingual models
a...
Proactive human-robot interaction (HRI) allows the receptionist robots t...
Despite the importance of unsupervised object detection, to the best of ...
Coarse-grained linguistic information, such as name entities or phrases,...
We propose a knowledge-enhanced approach, ERNIE-ViL, to learn joint
repr...
Current pre-training works in natural language generation pay little
att...
By integrating dynamics models into model-free reinforcement learning (R...
In this paper we propose to solve an important problem in recommendation...
It has been widely regarded that only considering the immediate user fee...
Recently, pre-trained models have achieved state-of-the-art results in
v...
We present a novel language representation model enhanced by knowledge c...
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge,
p...
Typical recommender systems push K items at once in the result page in t...
Combining deep neural networks with reinforcement learning has shown gre...
We present a new approach to learning grasp configurations for a novel o...