In recent years, reinforcement learning and imitation learning have show...
An eye-movement-based predicted trajectory guidance control (ePTGC) is
p...
Spiking neural networks (SNNs) have ultra-low energy consumption and hig...
The explosive growth of rumors with text and images on social media plat...
Hand tracking is an important aspect of human-computer interaction and h...
Existing dialogue models may encounter scenarios which are not
well-repr...
With a fast developing pace of geographic applications, automatable and
...
Power lines pose a significant safety threat to unmanned aerial vehicles...
In recent years, short Text Matching tasks have been widely applied in t...
Multi-label recognition (MLR) with incomplete labels is very challenging...
As a core task in location-based services (LBS) (e.g., navigation maps),...
Accurate and reliable prediction of driving intentions and future
trajec...
Accurate segmentation of power lines in aerial images is essential to en...
Deep reinforcement learning (DRL) requires the collection of plenty of
i...
This paper reviews recent deep-learning-based matting research and conce...
3D scene graph generation (SGG) has been of high interest in computer vi...
Glass is very common in our daily life. Existing computer vision systems...
Learning with sparse rewards is usually inefficient in Reinforcement Lea...
We propose a differentiable rendering algorithm for efficient novel view...
We introduce the task of implicit offensive text detection in dialogues,...
Inferring spatial relations in natural language is a crucial ability an
...
Dialogue State Tracking (DST) aims to keep track of users' intentions du...
Zero-shot learning (ZSL) aims to learn models that can recognize unseen ...
Embedding-based methods have attracted increasing attention in recent en...
Despite recent successes in natural language processing and computer vis...
Machine learning, especially deep learning, has greatly advanced molecul...
Pre-trained protein models (PTPMs) represent a protein with one fixed
em...
Self-supervised protein language models have proved their effectiveness ...
Visible-infrared person re-identification (VI-ReID) has been challenging...
Recent advances in machine learning and prevalence of digital medical im...
Molecular representation learning contributes to multiple downstream tas...
Spatial structures in the 3D space are important to determine molecular
...
Tactile sensing is critical for humans to perform everyday tasks. While
...
Most existing RGB-D salient object detection (SOD) models require large
...
Most existing cross-modality person re-identification works rely on
disc...
Image matting is an ill-posed problem that usually requires additional u...
Onfocus detection aims at identifying whether the focus of the individua...
Air pollution has altered the Earth radiation balance, disturbed the
eco...
This paper starts by deriving a factorization of the Loewner matrix penc...
With the goal of identifying pixel-wise salient object regions from each...
In this paper, we propose a fully automatic system for generating comic ...
An indispensable component in task-oriented dialogue systems is the dial...
Image matting is a long-standing problem in computer graphics and vision...
We present a novel method for testing the safety of self-driving vehicle...
It is very challenging for speech enhancement methods to achieves robust...
Recently, single-image super-resolution has made great progress owing to...
Asynchronous events on the continuous time domain, e.g., social media ac...
In this paper, we propose a new sampler for Bayesian learning that can
e...
In this paper, we present DEMC, a deep Dual-Encoder network to remove Mo...
Geometric deep learning is increasingly important thanks to the populari...