Large Language Models (LLMs) have made progress in various real-world ta...
Video analysis tasks rely heavily on identifying the pixels from differe...
On-device training is essential for user personalisation and privacy. Wi...
Approximate inference in Gaussian process (GP) models with non-conjugate...
Classifying the same event reported by different countries is of signifi...
With the continuous maturation and expansion of neural network technolog...
Embedding models have shown great power in knowledge graph completion (K...
Stroke can lead to the impaired motor ability of the patient's lower lim...
Deep neural networks (DNNs) achieve promising performance in visual
reco...
Source-free domain adaptation aims to adapt deep neural networks using o...
Multi-frame depth estimation generally achieves high accuracy relying on...
By leveraging their high mobility and small size, insects have been comb...
Test time adaptation (TTA) aims to adapt deep neural networks when recei...
Super-resolution, which aims to reconstruct high-resolution images from
...
Multi-modality medical imaging is crucial in clinical treatment as it ca...
In this paper, considering the balance of data/model privacy of model ow...
Creating a taxonomy of interests is expensive and human-effort intensive...
Online social as an extension of traditional life plays an important rol...
Recent image degradation estimation methods have enabled single-image
su...
Curated knowledge graphs encode domain expertise and improve the perform...
The neuron reconstruction from raw Optical Microscopy (OM) image stacks ...
A biological system is a complex network of heterogeneous molecular enti...
Gaussian process training decomposes into inference of the (approximate)...
This paper studies learning on text-attributed graphs (TAGs), where each...
Deep Learning has proliferated dramatically across consumer devices in l...
Graph Neural Networks (GNNs) have made tremendous progress in the graph
...
SpecAugment is a very effective data augmentation method for both HMM an...
Learning temporal correspondence from unlabeled videos is of vital impor...
Due to the difficulties of obtaining multimodal paired images in clinica...
People perceive the world with different senses, such as sight, hearing,...
Community search is a problem that seeks cohesive and connected subgraph...
The language of modal logic is capable of expressing first-order conditi...
The fusion of camera sensor and inertial data is a leading method for
eg...
In clinical practice, well-aligned multi-modal images, such as Magnetic
...
Different from handcrafted features, deep neural networks can automatica...
We introduce a novel frame-interpolation-based method for slice imputati...
The Covid-19 pandemic has forced the workforce to switch to working from...
Neural rendering with implicit neural networks has recently emerged as a...
The effectiveness of knowledge graph embedding (KGE) largely depends on ...
In this paper, we present Neural Adaptive Tomography (NeAT), the first
a...
Mean field approximation methodology has laid the foundation of modern
C...
Motion, as the most distinct phenomenon in a video to involve the change...
From the original theoretically well-defined spectral graph convolution ...
Building extraction from fine-resolution remote sensing images plays a v...
Simultaneous reconstruction of geometry and reflectance properties in
un...
Minimum circle circumnavigation is proposed in this paper, which is of
s...
Consider a home or office where multiple devices are running voice assis...
One-shot voice cloning aims to transform speaker voice and speaking styl...
Semantic segmentation of fine-resolution urban scene images plays a vita...
DFT is the numerical implementation of Fourier transform (FT), and it ha...