Megvii Technology Limited

∙ Beijing , China ∙ 0 followers

Face++ (http://www.faceplusplus.com/) is a new vision platform built by Megvii Inc. aiming at providing compact, powerful, and cross-platform vision service. Face++ uses the cutting-edge technology of computer vision and data mining to provide 3 core v...

Spatial-Scale Aligned Network for Fine-Grained Recognition

Existing approaches for fine-grained visual recognition focus on learnin...
01/05/2020 ∙ by Lizhao Gao, et al. ∙ 43 ∙ share

read it
PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation

In this work, we present a novel data-driven method for robust 6DoF obje...
11/11/2019 ∙ by Yisheng He, et al. ∙ 35 ∙ share

read it
PyRetri: A PyTorch-based Library for Unsupervised Image Retrieval by Deep Convolutional Neural Networks

Despite significant progress of applying deep learning methods to the fi...
05/02/2020 ∙ by Benyi Hu, et al. ∙ 25 ∙ share

read it
Stroke-based Artistic Rendering Agent with Deep Reinforcement Learning

Excellent painters can use only a few strokes to create a fantastic pain...
03/11/2019 ∙ by Zhewei Huang, et al. ∙ 18 ∙ share

read it
Data Uncertainty Learning in Face Recognition

Modeling data uncertainty is important for noisy images, but seldom expl...
03/25/2020 ∙ by Jie Chang, et al. ∙ 15 ∙ share

read it
STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification

Partial person re-identification (ReID) is a challenging task because on...
03/17/2019 ∙ by Hao Luo, et al. ∙ 14 ∙ share

read it
Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification

Due to its potential wide applications in video surveillance and other c...
02/29/2020 ∙ by Xing Fan, et al. ∙ 14 ∙ share

read it
Exploring Categorical Regularization for Domain Adaptive Object Detection

In this paper, we tackle the domain adaptive object detection problem, w...
03/20/2020 ∙ by Chang-Dong Xu, et al. ∙ 14 ∙ share

read it
M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Network

The present MVS methods with deep learning have an impressive performanc...
04/30/2020 ∙ by Baichuan Huang, et al. ∙ 14 ∙ share

read it
Re-ID Driven Localization Refinement for Person Search

Person search aims at localizing and identifying a query person from a g...
09/18/2019 ∙ by Chuchu Han, et al. ∙ 13 ∙ share

read it
WeightNet: Revisiting the Design Space of Weight Networks

We present a conceptually simple, flexible and effective framework for w...
07/23/2020 ∙ by Ningning Ma, et al. ∙ 12 ∙ share

read it
Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification

Vehicle re-identification is an important problem and becomes desirable ...
12/11/2018 ∙ by Xiu-Shen Wei, et al. ∙ 10 ∙ share

read it
Circle Loss: A Unified Perspective of Pair Similarity Optimization

This paper provides a pair similarity optimization viewpoint on deep fea...
02/25/2020 ∙ by Yifan Sun, et al. ∙ 10 ∙ share

read it
GridFace: Face Rectification via Learning Local Homography Transformations

In this paper, we propose a method, called GridFace, to reduce facial ge...
08/19/2018 ∙ by Erjin Zhou, et al. ∙ 6 ∙ share

read it
NPF-MVSNet: Normal and Pyramid Feature Aided Unsupervised MVS Network

We proposed an unsupervised learning-based network, named NPF-MVSNet, fo...
04/21/2020 ∙ by Baichuan Huang, et al. ∙ 6 ∙ share

read it
3DV: 3D Dynamic Voxel for Action Recognition in Depth Video

To facilitate depth-based 3D action recognition, 3D dynamic voxel (3DV) ...
05/12/2020 ∙ by Yancheng Wang, et al. ∙ 6 ∙ share

read it
Joint Multi-Dimension Pruning

We present joint multi-dimension pruning (named as JointPruning), a new ...
05/18/2020 ∙ by Zechun Liu, et al. ∙ 6 ∙ share

read it
Hierarchical Context Embedding for Region-based Object Detection

State-of-the-art two-stage object detectors apply a classifier to a spar...
08/04/2020 ∙ by Zhao-Min Chen, et al. ∙ 6 ∙ share

read it
Scene Text Recognition from Two-Dimensional Perspective

Inspired by speech recognition, recent state-of-the-art algorithms mostl...
09/18/2018 ∙ by Minghui Liao, et al. ∙ 4 ∙ share

read it
Scene Text Detection with Supervised Pyramid Context Network

Scene text detection methods based on deep learning have achieved remark...
11/21/2018 ∙ by Enze Xie, et al. ∙ 4 ∙ share

read it
2D-CTC for Scene Text Recognition

Scene text recognition has been an important, active research topic in c...
07/23/2019 ∙ by Zhaoyi Wan, et al. ∙ 3 ∙ share

read it
Semi-supervised Skin Detection by Network with Mutual Guidance

In this paper we present a new data-driven method for robust skin detect...
08/06/2019 ∙ by Yi He, et al. ∙ 3 ∙ share

read it
Video Inpainting by Jointly Learning Temporal Structure and Spatial Details

We present a new data-driven video inpainting method for recovering miss...
06/22/2018 ∙ by Chuan Wang, et al. ∙ 2 ∙ share

read it
Unified Perceptual Parsing for Scene Understanding

Humans recognize the visual world at multiple levels: we effortlessly ca...
07/26/2018 ∙ by Tete Xiao, et al. ∙ 2 ∙ share

read it
Semi-Supervised Video Salient Object Detection Using Pseudo-Labels

Deep learning-based video salient object detection has recently achieved...
08/12/2019 ∙ by Pengxiang Yan, et al. ∙ 2 ∙ share

read it
FA-GANs: Facial Attractiveness Enhancement with Generative Adversarial Networks on Frontal Faces

Facial attractiveness enhancement has been an interesting application in...
05/17/2020 ∙ by Jingwu He, et al. ∙ 2 ∙ share

read it
AutoAssign: Differentiable Label Assignment for Dense Object Detection

In this paper, we propose an anchor-free object detector with a fully di...
07/07/2020 ∙ by Benjin Zhu, et al. ∙ 2 ∙ share

read it
Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?

Face recognition performance improves rapidly with the recent deep learn...
01/20/2015 ∙ by Erjin Zhou, et al. ∙ 1 ∙ share

read it
Content-Aware Unsupervised Deep Homography Estimation

Robust homography estimation between two images is a fundamental task wh...
09/12/2019 ∙ by Jirong Zhang, et al. ∙ 1 ∙ share

read it
Weight-dependent Gates for Network Pruning

In this paper, we propose a simple and effective network pruning framewo...
07/04/2020 ∙ by Yun Li, et al. ∙ 1 ∙ share

read it
SOT for MOT

In this paper we present a robust tracker to solve the multiple object t...
12/04/2017 ∙ by Qizheng He, et al. ∙ 0 ∙ share

read it
AlignedReID: Surpassing Human-Level Performance in Person Re-Identification

In this paper, we propose a novel method called AlignedReID that extract...
11/22/2017 ∙ by Xuan Zhang, et al. ∙ 0 ∙ share

read it
Repulsion Loss: Detecting Pedestrians in a Crowd

Detecting individual pedestrians in a crowd remains a challenging proble...
11/21/2017 ∙ by Xinlong Wang, et al. ∙ 0 ∙ share

read it
Cascaded Pyramid Network for Multi-Person Pose Estimation

The topic of multi-person pose estimation has been largely improved rece...
11/20/2017 ∙ by Yilun Chen, et al. ∙ 0 ∙ share

read it
Face Attention Network: An Effective Face Detector for the Occluded Faces

The performance of face detection has been largely improved with the dev...
11/20/2017 ∙ by Jianfeng Wang, et al. ∙ 0 ∙ share

read it
MegDet: A Large Mini-Batch Object Detector

The improvements in recent CNN-based object detection works, from R-CNN ...
11/20/2017 ∙ by Chao Peng, et al. ∙ 0 ∙ share

read it
Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification

Person re-identification (ReID) is an important task in computer vision....
10/02/2017 ∙ by Qiqi Xiao, et al. ∙ 0 ∙ share

read it
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

We propose DoReFa-Net, a method to train convolutional neural networks t...
06/20/2016 ∙ by Shuchang Zhou, et al. ∙ 0 ∙ share

read it
Deep Learning with Low Precision by Half-wave Gaussian Quantization

The problem of quantizing the activations of a deep neural network is co...
02/03/2017 ∙ by Zhaowei Cai, et al. ∙ 0 ∙ share

read it
FastMask: Segment Multi-scale Object Candidates in One Shot

Objects appear to scale differently in natural images. This fact require...
12/28/2016 ∙ by Hexiang Hu, et al. ∙ 0 ∙ share

read it
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

We introduce an extremely computation-efficient CNN architecture named S...
07/04/2017 ∙ by Xiangyu Zhang, et al. ∙ 0 ∙ share

read it
Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks

Quantized Neural Networks (QNNs), which use low bitwidth numbers for rep...
06/22/2017 ∙ by Shuchang Zhou, et al. ∙ 0 ∙ share

read it
Point Linking Network for Object Detection

Object detection is a core problem in computer vision. With the developm...
06/12/2017 ∙ by Xinggang Wang, et al. ∙ 0 ∙ share

read it
What Can Help Pedestrian Detection?

Aggregating extra features has been considered as an effective approach ...
05/08/2017 ∙ by Jiayuan Mao, et al. ∙ 0 ∙ share

read it
EAST: An Efficient and Accurate Scene Text Detector

Previous approaches for scene text detection have already achieved promi...
04/11/2017 ∙ by Xinyu Zhou, et al. ∙ 0 ∙ share

read it
Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network

One of recent trends [30, 31, 14] in network architec- ture design is st...
03/08/2017 ∙ by Chao Peng, et al. ∙ 0 ∙ share

read it
Training Bit Fully Convolutional Network for Fast Semantic Segmentation

Fully convolutional neural networks give accurate, per-pixel prediction ...
12/01/2016 ∙ by He Wen, et al. ∙ 0 ∙ share

read it
UnitBox: An Advanced Object Detection Network

In present object detection systems, the deep convolutional neural netwo...
08/04/2016 ∙ by Jiahui Yu, et al. ∙ 0 ∙ share

read it
Scene Text Detection via Holistic, Multi-Channel Prediction

Recently, scene text detection has become an active research topic in co...
06/29/2016 ∙ by Cong Yao, et al. ∙ 0 ∙ share

read it
Exploiting Local Structures with the Kronecker Layer in Convolutional Networks

In this paper, we propose and study a technique to reduce the number of ...
12/31/2015 ∙ by Shuchang Zhou, et al. ∙ 0 ∙ share

read it

Megvii Technology Limited

Featured Researchers