Search Results - "2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition"

VizWiz Grand Challenge: Answering Visual Questions from Blind People by Gurari, Danna, Li, Qing, Stangl, Abigale J., Guo, Anhong, Lin, Chi, Grauman, Kristen, Luo, Jiebo, Bigham, Jeffrey P.

“…The study of algorithms to automatically answer visual questions currently is motivated by visual question answering (VQA) datasets constructed in artificial…”
Get full text

Deep Ordinal Regression Network for Monocular Depth Estimation by Fu, Huan, Gong, Mingming, Wang, Chaohui, Batmanghelich, Kayhan, Tao, Dacheng

“…Monocular depth estimation, which plays a crucial role in understanding 3D scene geometry, is an ill-posed problem. Recent methods have gained significant…”
Get full text

Squeeze-and-Excitation Networks by Hu, Jie, Shen, Li, Sun, Gang

“…Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information…”
Get full text

MobileNetV2: Inverted Residuals and Linear Bottlenecks by Sandler, Mark, Howard, Andrew, Zhu, Menglong, Zhmoginov, Andrey, Chen, Liang-Chieh

“…In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and…”
Get full text

Non-local Neural Networks by Wang, Xiaolong, Girshick, Ross, Gupta, Abhinav, He, Kaiming

“…Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations…”
Get full text

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices by Zhang, Xiangyu, Zhou, Xinyu, Lin, Mengxiao, Sun, Jian

“…We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing…”
Get full text

Cascade R-CNN: Delving Into High Quality Object Detection by Cai, Zhaowei, Vasconcelos, Nuno

“…In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU…”
Get full text

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs by Wang, Ting-Chun, Liu, Ming-Yu, Zhu, Jun-Yan, Tao, Andrew, Kautz, Jan, Catanzaro, Bryan

“…We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks…”
Get full text

StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation by Choi, Yunjey, Choi, Minje, Kim, Munyoung, Ha, Jung-Woo, Kim, Sunghun, Choo, Jaegul

“…Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and…”
Get full text

Residual Dense Network for Image Super-Resolution by Zhang, Yulun, Tian, Yapeng, Kong, Yu, Zhong, Bineng, Fu, Yun

“…A very deep convolutional neural network (CNN) has recently achieved great success for image super-resolution (SR) and offered hierarchical features as well…”
Get full text

Boosting Adversarial Attacks with Momentum by Dong, Yinpeng, Liao, Fangzhou, Pang, Tianyu, Su, Hang, Zhu, Jun, Hu, Xiaolin, Li, Jianguo

“…Deep neural networks are vulnerable to adversarial examples, which poses security concerns on these algorithms due to the potentially severe consequences…”
Get full text

High Performance Visual Tracking with Siamese Region Proposal Network by Li, Bo, Yan, Junjie, Wu, Wei, Zhu, Zheng, Hu, Xiaolin

“…Visual object tracking has been a fundamental topic in recent years and many deep learning based trackers have achieved state-of-the-art performance on…”
Get full text

DOTA: A Large-Scale Dataset for Object Detection in Aerial Images by Xia, Gui-Song, Bai, Xiang, Ding, Jian, Zhu, Zhen, Belongie, Serge, Luo, Jiebo, Datcu, Mihai, Pelillo, Marcello, Zhang, Liangpei

“…Object detection is an important and challenging problem in computer vision. Although the past decade has witnessed major advances in object detection in…”
Get full text

Frustum PointNets for 3D Object Detection from RGB-D Data by Qi, Charles R., Liu, Wei, Wu, Chenxia, Su, Hao, Guibas, Leonidas J.

“…In this work, we study 3D object detection from RGBD data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often…”
Get full text

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric by Zhang, Richard, Isola, Phillip, Efros, Alexei A., Shechtman, Eli, Wang, Oliver

“…While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite…”
Get full text

Generative Image Inpainting with Contextual Attention by Yu, Jiahui, Lin, Zhe, Yang, Jimei, Shen, Xiaohui, Lu, Xin, Huang, Thomas S.

“…Recent deep learning based approaches have shown promising results for the challenging task of inpainting large missing regions in an image. These methods can…”
Get full text

InLoc: Indoor Visual Localization with Dense Matching and View Synthesis by Taira, Hajime, Okutomi, Masatoshi, Sattler, Torsten, Cimpoi, Mircea, Pollefeys, Marc, Sivic, Josef, Pajdla, Tomas, Torii, Akihiko

“…We seek to predict the 6 degree-of-freedom (6DoF) pose of a query photograph with respect to a large indoor 3D map. The contributions of this work are…”
Get full text

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks by Gupta, Agrim, Johnson, Justin, Fei-Fei, Li, Savarese, Silvio, Alahi, Alexandre

“…Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate…”
Get full text

Maximum Classifier Discrepancy for Unsupervised Domain Adaptation by Saito, Kuniaki, Watanabe, Kohei, Ushiku, Yoshitaka, Harada, Tatsuya

“…In this work, we present a method for unsupervised domain adaptation. Many adversarial learning methods train domain classifier networks to distinguish the…”
Get full text

Path Aggregation Network for Instance Segmentation by Liu, Shu, Qi, Lu, Qin, Haifang, Shi, Jianping, Jia, Jiaya

“…The way that information propagates in neural networks is of great importance. In this paper, we propose Path Aggregation Network (PANet) aiming at boosting…”
Get full text