Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. We argue that the paths in a graph imply different semantics for different downstream tasks. However, traditional GNNs do not …
BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks. However, a major blocking issue of applying BERT to online services is that it …
Graph is a natural representation of data for a variety of real-word applications, such as knowledge graph mining, social network analysis and biological network comparison. For these applications, graph embedding is crucial as it provides vector …
It has been widely proven that modelling long-range dependencies in fully convolutional networks (FCNs) via global aggregation modules is critical for complex scene understanding tasks such as semantic segmentation and object detection. However, …
Exploiting long-range contextual information is key for pixel-wise prediction tasks such as semantic segmentation. In contrast to previous work that uses multi-scale feature fusion or dilated convolutions, we propose a novel graph-convolutional …
360 deg images are usually represented in either equirectangular projection (ERP) or multiple perspective projections. Different from the flat 2D images, the detection task is challenging for 360 deg images due to the distortion of ERP and the …
Resource balancing within complex transportation networks is one of the most important problems in real logistics domain. Traditional solutions on these problems leverage combinatorial optimization with demand and supply forecasting. However, the …