Graphs naturally appear in numerous application domains, ranging from social analysis,
bioinformatics to computer vision. The unique capability of graphs enables capturing the …

Lots of learning tasks require dealing with graph data which contains rich relation
information among elements. Modeling physics systems, learning molecular fingerprints …

Abstract The Non-Local Network (NLNet) presents a pioneering approach for capturing long-
range dependencies, via aggregating query-specific global context to each query position …

Convolution on 3D point clouds that generalized from 2D grid-like domains is widely
researched yet far from perfect. The standard convolution characterises feature …

Standard convolution is inherently limited for semantic segmentation of point cloud due to its
isotropy about features. It neglects the structure of an object, results in poor object …

The superior performance of Deformable Convolutional Networks arises from its ability to
adapt to the geometric variations of objects. Through an examination of its adaptive …

Knowledge graph completion (KGC) is a hot topic in knowledge graph construction and
related applications, which aims to complete the structure of knowledge graph by predicting …

Abstract Grammatical Error Correction (GEC) is the task of automatically detecting and
correcting errors in text. The task not only includes the correction of grammatical errors, such …

We introduce extreme summarization, a new single-document summarization task which
does not favor extractive strategies and calls for an abstractive modeling approach. The idea …

Generating a description of an image is called image captioning. Image captioning requires
recognizing the important objects, their attributes, and their relationships in an image. It also …