Related papers: Site-Net: Using global self-attention and real-spa…

Information extraction from semi-structured webpages provides valuable long-tailed facts for augmenting knowledge graph. Relational Web tables are a critical component containing additional entities and attributes of rich and diverse…

Machine learning (ML) methods have gained increasing popularity in exploring and developing new materials. More specifically, graph neural network (GNN) has been applied in predicting material properties. In this work, we develop a novel…

Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the long-term dependency problem is rarely realized for these very deep models, which…

Dynamic graph learning plays a pivotal role in modeling evolving relationships over time, especially for temporal link prediction tasks in domains such as traffic systems, social networks, and recommendation platforms. While…

Hypergraphs play a pivotal role in the modelling of data featuring higher-order relations involving more than two entities. Hypergraph neural networks emerge as a powerful tool for processing hypergraph-structured data, delivering…

Deep learning has led to a paradigm shift in artificial intelligence, including web, text and image search, speech recognition, as well as bioinformatics, with growing impact in chemical physics. Machine learning in general and deep…

Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical space. While convolutional neural networks have proven to be…

Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for the spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or…

Object-based attention is a key component of the visual system, relevant for perception, learning, and memory. Neurons tuned to features of attended objects tend to be more active than those associated with non-attended objects. There is a…

Computational methods that automatically extract knowledge from data are critical for enabling data-driven materials science. A reliable identification of lattice symmetry is a crucial first step for materials characterization and…

With the popularity of Transformer architectures in computer vision, the research focus has shifted towards developing computationally efficient designs. Window-based local attention is one of the major techniques being adopted in recent…

Triggered by the success of transformers in various visual tasks, the spatial self-attention mechanism has recently attracted more and more attention in the computer vision community. However, we empirically found that a typical vision…

Prevalence of deeper networks driven by self-attention is in stark contrast to underexplored point-based methods. In this paper, we propose groupwise self-attention as the basic block to construct our network: SepNet. Our proposed module…

Detecting and segmenting object instances is a common task in biomedical applications. Examples range from detecting lesions on functional magnetic resonance images, to the detection of tumours in histopathological images and extracting…

In this work, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although Convolutional Neural Networks (CNNs) have made substantial improvement on human attention prediction, it is…

Motivation: Real-world data often contain measurements with both continuous and discrete values. Despite the availability of many libraries, data sets with mixed data types require intensive pre-processing steps, and it remains a challenge…

In this paper, we propose a novel model named DemiNet (short for DEpendency-Aware Multi-Interest Network) to address the above two issues. To be specific, we first consider various dependency types between item nodes and perform…

Point clouds, being the simple and compact representation of surface geometry of 3D objects, have gained increasing popularity with the evolution of deep learning networks for classification and segmentation tasks. Unlike human, teaching…

Crystal-graph attention networks have emerged recently as remarkable tools for the prediction of thermodynamic stability and materials properties from unrelaxed crystal structures. Previous networks trained on two million materials…

We address the challenging task of human reaction generation, which aims to generate a corresponding reaction based on an input action. Most of the existing works do not focus on generating and predicting the reaction and cannot generate…