Yuanjun Xiong

is this you? claim profile

Applied Scientist at Amazon Rekognition since 2017, Postdoctoral Fellow at The Chinese University of Hong Kong 2016-2017, PhD Student at The Chinese University of Hong Kong from 2012-2016, Visiting Researcher at Google 2015

Learning to Recognize Patch-Wise Consistency for Deepfake Detection

We propose to detect Deepfake generated by face manipulation based on on...
12/16/2020 ∙ by Tianchen Zhao, et al. ∙ 3 ∙ share

read it
Positive-Congruent Training: Towards Regression-Free Model Updates

Reducing inconsistencies in the behavior of different versions of an AI ...
11/18/2020 ∙ by Sijie Yan, et al. ∙ 10 ∙ share

read it
SMOT: Single-Shot Multi Object Tracking

We present single-shot multi-object tracker (SMOT), a new tracking frame...
10/30/2020 ∙ by Wei Li, et al. ∙ 0 ∙ share

read it
Online Action Detection in Streaming Videos with Time Buffers

We formulate the problem of online temporal action detection in live str...
10/06/2020 ∙ by Bowen Zhang, et al. ∙ 6 ∙ share

read it
3D-Aided Data Augmentation for Robust Face Understanding

Data augmentation has been highly effective in narrowing the data gap an...
10/03/2020 ∙ by Yifan Xing, et al. ∙ 0 ∙ share

read it
Towards causal benchmarking of bias in face analysis algorithms

Measuring algorithmic bias is crucial both to assess algorithmic fairnes...
07/13/2020 ∙ by Guha Balakrishnan, et al. ∙ 0 ∙ share

read it
On Improving Temporal Consistency for Online Face Liveness Detection

In this paper, we focus on improving the online face liveness detection ...
06/11/2020 ∙ by Xiang Xu, et al. ∙ 0 ∙ share

read it
Motion Guided 3D Pose Estimation from Videos

We propose a new loss function, called motion loss, for the problem of m...
04/29/2020 ∙ by Jingbo Wang, et al. ∙ 0 ∙ share

read it
Towards Backward-Compatible Representation Learning

We propose a way to learn visual features that are compatible with previ...
03/26/2020 ∙ by Yantao Shen, et al. ∙ 4 ∙ share

read it
Action recognition with spatial-temporal discriminative filter banks

Action recognition has seen a dramatic performance improvement in the la...
08/20/2019 ∙ by Brais Martinez, et al. ∙ 26 ∙ share

read it
WIDER Face and Pedestrian Challenge 2018: Methods and Results

This paper presents a review of the 2018 WIDER Challenge on Face and Ped...
02/19/2019 ∙ by Chen Change Loy, et al. ∙ 6 ∙ share

read it
From Trailers to Storylines: An Efficient Way to Learn from Movies

The millions of movies produced in the human history are valuable resour...
06/14/2018 ∙ by Qingqiu Huang, et al. ∙ 2 ∙ share

read it
Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination

Neural net classifiers trained on data with annotated class labels can a...
05/05/2018 ∙ by Zhirong Wu, et al. ∙ 0 ∙ share

read it
Optimizing Video Object Detection via a Scale-Time Lattice

High-performance object detection relies on expensive convolutional netw...
04/16/2018 ∙ by Kai Chen, et al. ∙ 0 ∙ share

read it
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

Dynamics of human body skeletons convey significant information for huma...
01/23/2018 ∙ by Sijie Yan, et al. ∙ 0 ∙ share

read it
Face Detection through Scale-Friendly Deep Convolutional Networks

In this paper, we share our experience in designing a convolutional netw...
06/09/2017 ∙ by Shuo Yang, et al. ∙ 0 ∙ share

read it
Temporal Segment Networks for Action Recognition in Videos

Deep convolutional networks have achieved great success for image recogn...
05/08/2017 ∙ by Limin Wang, et al. ∙ 0 ∙ share

read it
UntrimmedNets for Weakly Supervised Action Recognition and Detection

Current action recognition methods heavily rely on trimmed videos for mo...
03/09/2017 ∙ by Limin Wang, et al. ∙ 0 ∙ share

read it
A Pursuit of Temporal Accuracy in General Activity Detection

Detecting activities in untrimmed videos is an important but challenging...
03/08/2017 ∙ by Yuanjun Xiong, et al. ∙ 0 ∙ share

read it
Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs

Convolutional Neural Networks (CNNs) have made remarkable progress on sc...
10/04/2016 ∙ by Limin Wang, et al. ∙ 0 ∙ share

read it
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

Deep convolutional networks have achieved great success for visual recog...
08/02/2016 ∙ by Limin Wang, et al. ∙ 0 ∙ share

read it
CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016

This paper presents the method that underlies our submission to the untr...
08/02/2016 ∙ by Yuanjun Xiong, et al. ∙ 0 ∙ share

read it
Towards Good Practices for Very Deep Two-Stream ConvNets

Deep convolutional networks have achieved great success for object recog...
07/08/2015 ∙ by Limin Wang, et al. ∙ 0 ∙ share

read it
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection

In this paper, we propose multi-stage and deformable deep convolutional ...
09/11/2014 ∙ by Wanli Ouyang, et al. ∙ 0 ∙ share

read it

Yuanjun Xiong

Featured Co-authors

Luc Van Gool

Xiaogang Wang

Wei Li

Hao Chen

Chen Change Loy

Meng Wang

Wanli Ouyang

Dahua Lin

Zhe Wang

Tao Mei

Hongsheng Li

Learning to Recognize Patch-Wise Consistency for Deepfake Detection

Positive-Congruent Training: Towards Regression-Free Model Updates

SMOT: Single-Shot Multi Object Tracking

Online Action Detection in Streaming Videos with Time Buffers

3D-Aided Data Augmentation for Robust Face Understanding

Towards causal benchmarking of bias in face analysis algorithms

On Improving Temporal Consistency for Online Face Liveness Detection

Motion Guided 3D Pose Estimation from Videos

Towards Backward-Compatible Representation Learning

Action recognition with spatial-temporal discriminative filter banks

WIDER Face and Pedestrian Challenge 2018: Methods and Results

From Trailers to Storylines: An Efficient Way to Learn from Movies

Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination

Optimizing Video Object Detection via a Scale-Time Lattice

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

Face Detection through Scale-Friendly Deep Convolutional Networks

Temporal Segment Networks for Action Recognition in Videos

UntrimmedNets for Weakly Supervised Action Recognition and Detection

A Pursuit of Temporal Accuracy in General Activity Detection

Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs

Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016

Towards Good Practices for Very Deep Two-Stream ConvNets

DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection