output
19942026
Showing 2018 · cs.CVShow all

82 papers · 2 filters

cs.CV2018★ 1 cited

Monocular 3D Pose Recovery via Nonconvex Sparsity with Theoretical Analysis

Jianqiao Wangni, Dahua Lin, Ji Liu +2

For recovering 3D object poses from 2D images, a prevalent method is to pre-train an over-complete dictionary of 3D basis poses. During testing, the detect…

cs.CV2018★ 6 cited

Pyramid Network with Online Hard Example Mining for Accurate Left Atrium Segmentation

Cheng Bian, Xin Yang, Jianqiang Ma +5

Accurately segmenting left atrium in MR volume can benefit the ablation procedure of atrial fibrillation. Traditional automated solutions often fail in relieving experts from the l…

cs.CV2018★ 88 cited

Efficient Attention: Attention with Linear Complexities

Zhuoran Shen, Mingyuan Zhang, Haiyu Zhao +2

Dot-product attention has wide applications in computer vision and natural language processing. However, its memory and computational costs grow quadratically with the input size.…

cs.CV2018★ 7 cited

Instance-level Facial Attributes Transfer with Geometry-Aware Flow

Weidong Yin, Ziwei Liu, Chen Change Loy

We address the problem of instance-level facial attribute transfer without paired training data, e.g. faithfully transferring the exact mustache from a source face to a target face…

cs.CV2018★ 6 cited

Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct?

Ping Luo, Zhanglin Peng, Jiamin Ren +1

Yes, they do. This work investigates a perspective for deep learning: whether different normalization layers in a ConvNet require different normalizers. This is the first step towa…

cs.CV2018★ 67 cited

Gradient Harmonized Single-stage Detector

Buyu Li, Yu Liu, Xiaogang Wang

Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the two well-known disharmonies during training,…

cs.CV2018★ 13 cited

Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks

Yuenan Hou, Zheng Ma, Chunxiao Liu +1

The training of many existing end-to-end steering angle prediction models heavily relies on steering angles as the supervisory signal. Without learning from much richer contexts, t…

cs.CV2018★ 24 cited

3D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Training

Yingda Xia, Fengze Liu, Dong Yang +6

While making a tremendous impact in various fields, deep neural networks usually require large amounts of labeled data for training which are expensive to collect in many applicati…

cs.CV2018★ 71 cited

TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents

Yuexin Ma, Xinge Zhu, Sibo Zhang +3

To safely and efficiently navigate in complex urban traffic, autonomous vehicles must make responsible predictions in relation to surrounding traffic-agents (vehicles, bicycles, pe…

cs.CV2018★ 254 cited

Image Inpainting via Generative Multi-column Convolutional Neural Networks

Yi Wang, Xin Tao, Xiaojuan Qi +2

In this paper, we propose a generative multi-column network for image inpainting. This network synthesizes different image components in a parallel manner within one stage. To bett…

cs.CV2018★ 20 cited

Sequential Context Encoding for Duplicate Removal

Lu Qi, Shu Liu, Jianping Shi +1

Duplicate removal is a critical step to accomplish a reasonable amount of predictions in prevalent proposal-based object detection frameworks. Albeit simple and effective, most pre…

cs.CV2018★ 36 cited

Visual Semantic Navigation using Scene Priors

Wei Yang, Xiaolong Wang, Ali Farhadi +2

How do humans navigate to target objects in novel scenes? Do we use the semantic/functional priors we have built over years to efficiently search and navigate? For example, to sear…

cs.CV2018★ 19 cited

PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention

Yongbin Sun, Yue Wang, Ziwei Liu +2

Generating 3D point clouds is challenging yet highly desired. This work presents a novel autoregressive model, PointGrow, which can generate diverse and realistic point cloud sampl…

cs.CV2018

Binocular Tone Mapping with Improved Overall Contrast and Local Details

Zhuming Zhang, Xinghong Hu, Xueting Liu +1

Tone mapping is a commonly used technique that maps the set of colors in high-dynamic-range (HDR) images to another set of colors in low-dynamic-range (LDR) images, to fit the need…

cs.CV2018★ 1.2k cited

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

Xintao Wang, Ke Yu, Shixiang Wu +6

The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the ha…

cs.CV2018★ 99 cited

Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection

Yongcheng Liu, Lu Sheng, Jing Shao +3

Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs)…

cs.CV2018★ 235 cited

Deep Learning for Generic Object Detection: A Survey

Li Liu, Wanli Ouyang, Xiaogang Wang +4

Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural…

cs.CV2018★ 3 cited

Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition

Xiaohang Zhan, Ziwei Liu, Junjie Yan +2

Face recognition has witnessed great progress in recent years, mainly attributed to the high-capacity model designed and the abundant labeled data collected. However, it becomes mo…

cs.CV2018★ 15 cited

Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation

Xinge Zhu, Hui Zhou, Ceyuan Yang +2

Due to the expensive and time-consuming annotations (e.g., segmentation) for real-world images, recent works in computer vision resort to synthetic data. However, the performance o…

cs.CV2018★ 44 cited

Localization Guided Learning for Pedestrian Attribute Recognition

Pengze Liu, Xihui Liu, Junjie Yan +1

Pedestrian attribute recognition has attracted many attentions due to its wide applications in scene understanding and person analysis from surveillance videos. Existing methods tr…

cs.CV2018★ 33 cited

Learning Monocular Depth by Distilling Cross-domain Stereo Networks

Xiaoyang Guo, Hongsheng Li, Shuai Yi +2

Monocular depth estimation aims at estimating a pixelwise depth map for a single image, which has wide applications in scene understanding and autonomous driving. Existing supervis…

cs.CV2018★ 10 cited

Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos

Zhaoyang Zhang, Zhanghui Kuang, Ping Luo +2

Video Analytics Software as a Service (VA SaaS) has been rapidly growing in recent years. VA SaaS is typically accessed by users using a lightweight client. Because the transmissio…

cs.CV2018★ 11 cited

Subsampled Turbulence Removal Network

Wai Ho Chak, Chun Pong Lau, Lok Ming Lui

We present a deep-learning approach to restore a sequence of turbulence-distorted video frames from turbulent deformations and space-time varying blurs. Instead of requiring a mass…

cs.CV2018★ 30 cited

Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model

Xiaomeng Li, Lequan Yu, Hao Chen +2

Automatic skin lesion segmentation on dermoscopic images is an essential component in computer-aided diagnosis of melanoma. Recently, many fully supervised deep learning based meth…