Whole-body pose estimation localizes the human body, hand, face, and foo...
Audio-driven portrait animation aims to synthesize portrait videos that ...
Given an arbitrary audio clip, audio-driven 3D facial animation aims to
...
The field of protein folding research has been greatly advanced by deep
...
Language-based colorization produces plausible and visually pleasing col...
The performance of Large Language Models (LLMs) in reasoning tasks depen...
Along with the development of systems for natural language understanding...
This paper raises the new task of Fisheye Semantic Completion (FSC), whe...
3D GAN inversion aims to achieve high reconstruction fidelity and reason...
ChatGPT is a powerful large language model (LLM) that has made remarkabl...
The insurance industry is shifting their sales mode from offline to onli...
Lipreading refers to understanding and further translating the speech of...
Drug combination therapy is a well-established strategy for disease trea...
Dialogue summarization has recently garnered significant attention due t...
Camouflaged objects are seamlessly blended in with their surroundings, w...
Deep Active Learning (DAL) has been advocated as a promising method to r...
By adopting popular pixel-wise loss, existing methods for defocus deblur...
Dialog systems are often designed or trained to output human-like respon...
Automatic human matting is highly desired for many real applications. We...
Rain is transparent, which reflects and refracts light in the scene to t...
In terms of 3D imaging speed and system cost, the single-camera system
p...
The Autonomous Truck-Mounted Attenuator (ATMA) system is a lead-follower...
This paper reports on progress towards building an online language learn...
Audio commands are a preferred communication medium to keep inspectors i...
RNA structure determination and prediction can promote RNA-targeted drug...
Action classification has made great progress, but segmenting and recogn...
It is a challenging task to recover all-in-focus image from a single def...
Multi-action dialog policy (MADP), which generates multiple atomic dialo...
In this work, we propose three Braess-Sarazin-type multigrid relaxation
...
Recently vision transformer has achieved tremendous success on image-lev...
In the whole aircraft structural optimization loop, thermal analysis pla...
Recent state-of-the-art one-stage instance segmentation model SOLO divid...
The task of hot-refresh model upgrades of image retrieval systems plays ...
Adversarial examples (AEs) pose severe threats to the applications of de...
Existing active learning studies typically work in the closed-set settin...
Conversational recommendation systems (CRS) engage with users by inferri...
Knowledge-grounded dialogue systems are challenging to build due to the ...
Muilti-modality data are ubiquitous in biology, especially that we have
...
The reconstruction of microbial genomes from large metagenomic datasets ...
We propose an eigensolver and the corresponding package, GCGE, for solvi...
Identifying the targets of an antimicrobial peptide is a fundamental ste...
We study anomaly detection for the case when the normal class consists o...
User interest exploration is an important and challenging topic in
recom...
Graph neural networks (GNNs) have received tremendous attention due to t...
Reducing traffic fatalities and serious injuries is a top priority of th...
Over 600,000 bridges in the U.S. must be inspected every two years to
id...
In this study, a novel physics-data-driven Bayesian method named Heat
Co...
Colorization has attracted increasing interest in recent years. Classic
...
Nowadays, artificial neural networks are widely used for users' online t...
The selective visual attention mechanism in the human visual system (HVS...