The world of sports intrinsically involves fast and accurate motion that is not only challenging
for competitors to master, but can be difficult for coaches and trainers to analyze, and for …

With the extensive application of deep learning (DL) algorithms in recent years, eg, for
detecting Android malware or vulnerable source code, artificial intelligence (AI) and …

Vision-based monocular human pose estimation, as one of the most fundamental and
challenging problems in computer vision, aims to obtain posture of the human body from …

We investigate the problem of producing structured graph representations of visual scenes.
Our work analyzes the role of motifs: regularly appearing substructures in scene graphs. We …

The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning
algorithms to reach near-human semantic classification performance at tasks such as visual …

Abstract Since Convolutional Neural Network (CNN) won the image classification
competition 202 (ILSVRC12), a lot of attention has been paid to deep layer CNN study. The …

In this work, we revisit the global average pooling layer proposed in [13], and shed light on
how it explicitly enables the convolutional neural network (CNN) to have remarkable …

We propose an end-to-end-trainable attention module for convolutional neural network
(CNN) architectures built for image classification. The module takes as input the 2D feature …

We present a model that generates natural language descriptions of images and their
regions. Our approach leverages datasets of images and their sentence descriptions to …

Scene recognition is one of the hallmark tasks of computer vision, allowing definition of a
context for object recognition. Whereas the tremendous recent progress in object recognition …