Search Results - "2019 IEEE/CVF International Conference on Computer Vision (ICCV)"

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks by Ding, Xiaohan, Guo, Yuchen, Ding, Guiguang, Han, Jungong

“…As designing appropriate Convolutional Neural Network (CNN) architecture in the context of a given application usually involves heavy human works or numerous…”
Get full text

GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing by Liu, Xiaohong, Ma, Yongrui, Shi, Zhihao, Chen, Jun

“…We propose an end-to-end trainable Convolutional Neural Network (CNN), named GridDehazeNet, for single image dehazing. The GridDehazeNet consists of three…”
Get full text

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better by Kupyn, Orest, Martyniuk, Tetiana, Wu, Junru, Wang, Zhangyang

“…We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-V2, which considerably boosts…”
Get full text

Tex2Shape: Detailed Full Human Body Geometry From a Single Image by Alldieck, Thiemo, Pons-Moll, Gerard, Theobalt, Christian, Magnor, Marcus

“…We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including…”
Get full text

FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape From Single RGB Images by Zimmermann, Christian, Ceylan, Duygu, Yang, Jimei, Russell, Bryan, Argus, Max J., Brox, Thomas

“…Estimating 3D hand pose from single RGB images is a highly ambiguous problem that relies on an unbiased training dataset. In this paper, we analyze…”
Get full text

Online Hyper-Parameter Learning for Auto-Augmentation Strategy by Lin, Chen, Guo, Minghao, Li, Chuming, Yuan, Xin, Wu, Wei, Yan, Junjie, Lin, Dahua, Ouyang, Wanli

“…Data augmentation is critical to the success of modern deep learning techniques. In this paper, we propose Online Hyper-parameter Learning for…”
Get full text

ERL-Net: Entangled Representation Learning for Single Image De-Raining by Wang, Guoqing, Sun, Changming, Sowmya, Arcot

“…Despite the significant progress achieved in image de-raining by training an encoder-decoder network within the image-to-image translation formulation, blurry…”
Get full text

A Learned Representation for Scalable Vector Graphics by Lopes, Raphael Gontijo, Ha, David, Eck, Douglas, Shlens, Jonathon

“…Dramatic advances in generative models have resulted in near photographic quality for artificially rendered faces, animals and other objects in the natural…”
Get full text

Learning the Model Update for Siamese Trackers by Zhang, Lichao, Gonzalez-Garcia, Abel, Weijer, Joost Van De, Danelljan, Martin, Khan, Fahad Shahbaz

“…Siamese approaches address the visual tracking problem by extracting an appearance template from the current frame, which is used to localize the target in the…”
Get full text

IL2M: Class Incremental Learning With Dual Memory by Belouadah, Eden, Popescu, Adrian

“…This paper presents a class incremental learning (IL) method which exploits fine tuning and a dual memory to reduce the negative effect of catastrophic…”
Get full text

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features by Yun, Sangdoo, Han, Dongyoon, Chun, Sanghyuk, Oh, Seong Joon, Yoo, Youngjoon, Choe, Junsuk

“…Regional dropout strategies have been proposed to enhance performance of convolutional neural network classifiers. They have proved to be effective for guiding…”
Get full text

FCOS: Fully Convolutional One-Stage Object Detection by Tian, Zhi, Shen, Chunhua, Chen, Hao, He, Tong

“…We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic…”
Get full text

Searching for MobileNetV3 by Howard, Andrew, Sandler, Mark, Chen, Bo, Wang, Weijun, Chen, Liang-Chieh, Tan, Mingxing, Chu, Grace, Vasudevan, Vijay, Zhu, Yukun, Pang, Ruoming, Adam, Hartwig, Le, Quoc

“…We present the next generation of MobileNets based on a combination of complementary search techniques as well as a novel architecture design. MobileNetV3 is…”
Get full text

CenterNet: Keypoint Triplets for Object Detection by Duan, Kaiwen, Bai, Song, Xie, Lingxi, Qi, Honggang, Huang, Qingming, Tian, Qi

“…In object detection, keypoint-based approaches often experience the drawback of a large number of incorrect object bounding boxes, arguably due to the lack of…”
Get full text

SlowFast Networks for Video Recognition by Feichtenhofer, Christoph, Fan, Haoqi, Malik, Jitendra, He, Kaiming

“…We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii)…”
Get full text

CCNet: Criss-Cross Attention for Semantic Segmentation by Huang, Zilong, Wang, Xinggang, Huang, Lichao, Huang, Chang, Wei, Yunchao, Liu, Wenyu

“…Full-image dependencies provide useful contextual information to benefit visual understanding problems. In this work, we propose a Criss-Cross Network (CCNet)…”
Get full text

YOLACT: Real-Time Instance Segmentation by Bolya, Daniel, Zhou, Chong, Xiao, Fanyi, Lee, Yong Jae

“…We present a simple, fully-convolutional model for real-time instance segmentation that achieves 29.8 mAP on MS COCO at 33.5 fps evaluated on a single Titan…”
Get full text

KPConv: Flexible and Deformable Convolution for Point Clouds by Thomas, Hugues, Qi, Charles R., Deschaud, Jean-Emmanuel, Marcotegui, Beatriz, Goulette, Francois, Guibas, Leonidas

“…We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation…”
Get full text

TSM: Temporal Shift Module for Efficient Video Understanding by Lin, Ji, Gan, Chuang, Han, Song

“…The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost. Conventional 2D…”
Get full text

Moment Matching for Multi-Source Domain Adaptation by Peng, Xingchao, Bai, Qinxun, Xia, Xide, Huang, Zijun, Saenko, Kate, Wang, Bo

“…Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where…”
Get full text