Video saliency prediction and detection are thriving research domains th...
Auditory Attention Detection (AAD) aims to detect target speaker from br...
Quantization emerges as one of the most promising approaches for deployi...
The development of learning-based methods has greatly improved the detec...
Emerging tools bring forth fresh approaches to work, and the field of na...
The mainstream of data-driven abstractive summarization models tends to
...
Traffic prediction is essential for the progression of Intelligent
Trans...
Instance segmentation in electron microscopy (EM) volumes poses a signif...
Self-supervised sound source localization is usually challenged by the
m...
Recent stereo matching networks achieves dramatic performance by introdu...
Graph collaborative filtering (GCF) has gained considerable attention in...
DeepFake based digital facial forgery is threatening public media securi...
Graph neural networks (GNNs) have pioneered advancements in graph
repres...
Vision-Language Pretraining (VLP) has demonstrated remarkable capabiliti...
In this paper, we study the (geospatial) ontologies we are interested in...
A ReLU network is a piecewise linear function over polytopes. Figuring o...
Rutting of asphalt pavements is a crucial design criterion in various
pa...
A common explanation for the failure of out-of-distribution (OOD)
genera...
The amount of data has growing significance in exploring cutting-edge
ma...
Incorporating the audio stream enables Video Saliency Prediction (VSP) t...
Large vision Transformers (ViTs) driven by self-supervised pre-training
...
Determining causal effects of temporal multi-intervention assists
decisi...
Existing graph contrastive learning (GCL) typically requires two forward...
We identify the average dose-response function (ADRF) for a continuously...
Transformers have demonstrated a competitive performance across a wide r...
Data valuation, especially quantifying data value in algorithmic predict...
Generative Adversarial Networks (GANs) have paved the path towards entir...
To investigate causal mechanisms, causal mediation analysis decomposes t...
Single-pixel imaging (SPI) is a novel optical imaging technique by repla...
News representation and user-oriented modeling are both essential for ne...
Functional data often arise in the areas where the causal treatment effe...
When signals propagate through forest areas, they will be affected by
en...
Learning the underlying casual structure, represented by Directed Acycli...
This paper concerns estimation and inference for treatment effects in de...
Hazard and Operability Analysis (HAZOP) is a powerful safety analysis
te...
Recently, masked image modeling (MIM) has offered a new methodology of
s...
State-of-the-art causal discovery methods usually assume that the
observ...
With its growing use in safety/security-critical applications, Deep Lear...
Advanced deep neural networks (DNNs), designed by either human or AutoML...
Single-pixel imaging (SPI) is a novel optical imaging technique by repla...
Graph contrastive learning (GCL) is the most representative and prevalen...
Adversarial training has been shown to be one of the most effective
appr...
DeepFake based digital facial forgery is threatening the public media
se...
Talking face generation with great practical significance has attracted ...
Multi-modal based speech separation has exhibited a specific advantage o...
Active speaker detection and speech enhancement have become two increasi...
This work targets automated designing and scaling of Vision Transformers...
PAC-Bayesian is an analysis framework where the training error can be
ex...
Distributed machine learning (DML) over time-varying networks can be an
...
Generating 3D city models rapidly is crucial for many applications. Mono...