Jiankang Deng

About Me ([CV] [ DBLP ] [ Google Scholar])

I am a Ph.D. student in the Intelligent Behaviour Understanding Group (IBUG) at Imperial College London (ICL), supervised by Stefanos Zafeiriou and funded by the Imperial President's PhD Scholarships. I am in the project of EPSRC FACER2VM (Face Matching for Automatic Identity Retrieval, Recognition, Verification and Management). My Ph.D. research topic is face analysis.

Before coming to IBUG, I obtained my master and bachelor degrees from Nanjing University of Information Science and Technology. During my master study, I was with the BDAT Lab under the supervision of Prof. Qingshan Liu, and I worked closely with Prof. Dacheng Tao.

News

2018-01-23: I have launched a 2D and 3D face analysis project named InsightFace, which aims at providing better, faster and smaller face analysis algorithms with public available training data. Currently, we have achieved the state-of-the-art performance on MegaFace Challenge.
2017-07-17: In the last three years, I have collected 20/43 yellow bars (10 in 2017, 5 in 2016 and 5 in 2015) from the ImageNet Large Scale Visual Recognition Challenge (ILSVRC). ImageNet Challenge is the most prestigious competition commonly known as the Olympics of computer vision.

Academic Presentations

CVPR 2017, ActivityNet Large Scale Activity Recognition Challenge, Improve Untrimmed Video Classification and Action Localization by Human and Object Tubelets
CVPR 2017, Beyond ImageNet Large Scale Visual Recognition Challenge, Speed/Accuracy Trade-offs for Object Detection from Video
CVPR 2017, Beyond ImageNet Large Scale Visual Recognition Challenge, BDAT Object Detection
ECCV 2016, ImageNet and COCO Visual Recognition Challenges, Efficient Object Detection From Videos
ICCV 2015, ImageNet and MS COCO Visual Recognition Challenges, Cascade Region Regression for Robust Object Detection

Academic Competitions

iQIYI-VID 2018: iQIYI Celebrity Video Identification, Rank 1st.
ActivityNet 2017: Untrimmed Video Classification, Rank 1st.
ILSVRC 2017: Object detection with provided/additional training data, Rank 1st.
ILSVRC 2017: Object detection from video with provided/additional training data, Rank 1st.
ILSVRC 2017: Object detection/tracking from video with provided/additional training data, Rank 1st.
ILSVRC 2016: Object detection from video with provided/additional training data, Rank 1st.
ILSVRC 2016: Object detection/tracking from video with additional training data, Rank 1st.
ILSVRC 2015: Object detection with additional training data, Rank 1st.
ILSVRC 2015: Object classification with additional training data, Rank 1st.
ILSVRC 2015: Object detection from video with additional training data, Rank 1st.
300-VW 2015: Face detection, alignment and tracking from videos, Rank 1st.
300-W 2014: Face detection and alignment from images, Rank 1st (Academic).

Datasets

The 3D Menpo Facial Landmark Tracking Challenge
S. Zafeiriou, G. Chrysos, A. Roussos, E. Ververas, J. Deng and G. Trigeorgis
in ICCVW, 2017.
[ Paper ] [ Project Page]
Full pose 3D face alignment dataset (84 landmarks)

The Menpo Facial Landmark Localisation Challenge: A step closer to the solution
S. Zafeiriou, G. Trigeorgis, G. Chrysos, J. Deng and J. Shen
in CVPRW, 2017.
[ Paper ] [ Project Page]
Multi-view 2D face alignment dataset
(68 landmarks for semi-frontal faces and 39 landmarks for profile faces)

AgeDB: the first manually collected, in-the-wild age database
S. Moschoglou, A. Papaioannou, C. Sagonas, J. Deng, I. Kotsia, and S. Zafeiriou
in CVPRW, 2017.
[ Paper ] [ Project Page]
Manually collected in-the-wild age dataset

Face Recognition

ArcFace: Additive Angular Margin Loss for Deep Face Recognition
J. Deng, J. Guo, N. Xue and S. Zafeiriou
in CVPR (Oral), 2019.
[ Paper ] [ Code ]
Angular margin loss for deep face recognition

UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
J. Deng, S. Cheng, N. Xue, Y. Zhou and S. Zafeiriou
in CVPR, 2018.
[ Paper ] [ Data ]
UV completion

Marginal Loss for Deep Face Recognition
J. Deng, Y.Zhou and S. Zafeiriou
in CVPRW, 2017.
[ Paper ] [ Poster] [ NIST Report]
[ AgeDB_v1]
Simple setting of data, network and loss for deep face recognition

Face Alignment

The Menpo Benchmark for Multi-pose 2D and 3D Facial Landmark Localisation and Tracking
J. Deng, A. Roussos, G. Chrysos, E. Ververas, I. Kotsia, J. Shen, S. Zafeiriou
in IJCV, 2018.
[ Paper ] [ Data ]
2D and 3D face alignment

Stacked Dense U-Nets with Dual Transformers for Robust Face Alignment
J. Guo, J. Deng, N. Xue and S. Zafeiriou
in BMVC, 2018.
[ Paper ] [ Code ]
2D and 3D face alignment

Cascade Multi-view Hourglass Model for Robust 3D Face Alignment
J. Deng, Y. Zhou, S. Cheng and S. Zafeiriou
in FG, 2018.
[ Paper ] [ Code ]
Full pose 3D style face alignment

Joint Multi-view Face Alignment in the Wild
J. Deng, G. Trigeorgis, Y. Zhou, and S. Zafeiriou
in TIP, 2019.
[ Paper ] [ 300VW Demo Results]
[ 2D Face Alignment Image Data]
Joint multi-view face alignment

Adaptive Cascade Regression Model for Robust Face Alignment
Q. Liu, J. Deng, J. Yang, G. Liu, and D. Tao
in TIP, 2017.
[ Paper ]
Adaptive shape constraint for face alignment under occlusion

Dual Sparse Constrained Cascade Regression for Robust Face Alignment
Q. Liu, J. Deng, and D. Tao
in TIP, 2016.
[ Paper ]
Face alignment model compression by sparse constraint

Facial Shape Tracking via Spatio-temporal Cascade Shape Regression
J. Yang, J. Deng, K. Zhang and Q. Liu
in ICCVW, 2015.
[ Paper ] [ Android Demo Binary Feature]
[ 300VW Frame-wise Results]
Winner of 300VW (Face detection, alignment and tracking from videos)

M3CSR: Multi-view, Multi-scale and Multi-component Cascade Shape Regression
J. Deng, J. Yang, Q. Liu and D. Tao
in Image Vision Computing, 2014.
[ Paper ] [ Android Demo HoG] [ Demo HoG vs Binary Feature]
Academic winner of 300W (Face detection and alignment from images)

Robust PCA

Side Information for Face Completion: a Robust PCA Approach
N. Xue, J. Deng, S. Cheng, I. Panagakis and S. Zafeiriou
in TPAMI, 2019.
[ Paper ]
Face completion by RPCA

Informed Non-convex Robust Principal Component Analysis with Features
N. Xue, J. Deng, I. Panagakis and S. Zafeiriou
in AAAI (Oral), 2018.
[ Paper ] [ Slide ]
Non-convex RPCA