End-to-end task-oriented dialogue (TOD) systems have achieved promising
...
The massive successes of large language models (LLMs) encourage the emer...
Recent months have seen the emergence of a powerful new trend in which l...
Domain generalization (DG) aims to learn a robust model from source doma...
Token interaction operation is one of the core modules in MLP-based mode...
Despite advancements in conversational AI, language models encounter
cha...
Automated medical image classification is the key component in intellige...
The success of the GPT series proves that GPT can extract general inform...
Automated medical image segmentation inherently involves a certain degre...
Segment Anything Model (SAM) has revolutionized the way of segmentation....
Advancements in adapting deep convolution architectures for Spiking Neur...
Existing recommender systems face difficulties with zero-shot items, i.e...
Test time adaptation (TTA) aims to adapt deep neural networks when recei...
In this paper, considering the balance of data/model privacy of model ow...
When learning task-oriented dialogue (ToD) agents, reinforcement learnin...
Domain Generalization (DG) is a fundamental challenge for machine learni...
Dense retrievers have made significant strides in obtaining state-of-the...
Quantifying the perceptual similarity of two images is a long-standing
p...
Unsupervised image semantic segmentation(UISS) aims to match low-level v...
Partial least square regression (PLSR) is a widely-used statistical mode...
Medical image synthesis has attracted increasing attention because it co...
Heatmap regression methods have dominated face alignment area in recent ...
Face detection is to search all the possible regions for faces in images...
In this work, we focus on a more challenging few-shot intent detection
s...
Nowadays, most existing blind image quality assessment (BIQA) models 1) ...
Radiomic representations can quantify properties of regions of interest ...
Multi-modal medical image segmentation plays an essential role in clinic...
Shape modeling and reconstruction from raw point clouds of objects stand...
Tackling domain shifts in multi-centre and multi-vendor data sets remain...
MultiWOZ is a well-known task-oriented dialogue dataset containing over
...
Temporal modeling is key for action recognition in videos. It normally
c...
Domain adaptation in healthcare data is a potentially critical component...
Analysis and modeling of the ventricles and myocardium are important in ...
Recent studies on medical image synthesis reported promising results usi...
Quantification of cerebral white matter hyperintensities (WMH) of presum...
Nowadays, an increasing number of customers are in favor of using E-comm...
With the development of cloud computing and big data, the reliability of...
The increasing demand for on-device deep learning services calls for a h...
Segmentation of both large and small white matter hyperintensities/lesio...
Zero-shot learning (ZSL) aims to recognize unseen image categories by
le...
In this paper, we consider the problem of leveraging existing fully labe...
White matter hyperintensities (WMH) are commonly found in the brains of
...
Person re-identification (ReID) is an important task in wide area video
...