In the static declaration strategy that is used in toolkits like Theano, CNTK, and TensorFlow, the user first defines a computation graph (a symbolic representation of the computation), and then examples are fed into an engine that executes this computation and computes its derivatives.
In this paper, we propose EFANNA, an extremely fast approximate nearest neighbor search algorithm based on $k$NN Graph.
We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017).
Second, the second-order information of the skeleton data, i. e., the length and orientation of the bones, is rarely investigated, which is naturally more informative and discriminative for the human action recognition.
In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods.
Ranked #3 on Skeleton Based Action Recognition on UAV-Human
The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a limited number of training instances per class.
In this paper, we propose a novel unified relational reasoning graph network for arbitrary shape text detection.
In contrast to the literature where local patterns in 3D point clouds are captured by customized convolutional operators, in this paper we study the problem of how to effectively and efficiently project such point clouds into a 2D image space so that traditional 2D convolutional neural networks (CNNs) such as U-Net can be applied for segmentation.
Ranked #5 on 3D Part Segmentation on ShapeNet-Part
Deep NLP models benefit from underlying structures in the data---e. g., parse trees---typically extracted using off-the-shelf parsers.