Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years. Over the past two decades, we have …
Y Xiao, Z Tian, J Yu, Y Zhang, S Liu, S Du… - Multimedia Tools and …, 2020 - Springer
With the rapid development of deep learning techniques, deep convolutional neural networks (DCNNs) have become more important for object detection. Compared with …
G Brazil, X Liu - Proceedings of the IEEE/CVF international …, 2019 - openaccess.thecvf.com
Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been …
R Yu, A Li, CF Chen, JH Lai… - Proceedings of the …, 2018 - openaccess.thecvf.com
To reduce the significant redundancy in deep Convolutional Neural Networks (CNNs), most existing methods prune neurons by only considering the statistics of an individual layer or …
P Zhou, X Han, VI Morariu… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
Image manipulation detection is different from traditional semantic object detection because it pays more attention to tampering artifacts than to image content, which suggests that richer …
We consider open-domain queston answering (QA) where answers are drawn from either a corpus, a knowledge base (KB), or a combination of both of these. We focus on a setting in …
Detecting objects in aerial images is challenging for at least two reasons:(1) target objects like pedestrians are very small in pixels, making them hardly distinguished from surrounding …
Action recognition is an open and challenging problem in computer vision. While current state-of-the-art models offer excellent recognition results, their computational expense limits …
Deep neural networks have become a mainstream approach to interactive segmentation. As we show in our experiments, while for some images a trained network provides accurate …