Jifeng Dai

(代季峰)
Executive Research Director, SenseTime Group Ltd

Principle Research Manager
Visual Computing Group, Microsoft Research Asia
Email: daijifeng -at- sensetime.com
Github: https://github.com/msracver https://github.com/daijifeng001

News

I am founding a foundamental research team, and an applied research team at SenseTime Research. If you are interested in internship, Ph.D. program, foundamental research position, or applied researcher / developer positions related to computer vision or deep learning, please send me an email.

Short Bio

Currently, I am an Executive Research Director at SenseTime Research. I am founding a foundamental research team, and an applied research team. My current research focus is on deep learning for high-level vision, especially for semantic segmentation and object detection.

Prior to that, I was a Principle Research Manager in Visual Computing Group at Microsoft Research Asia (MSRA), where I spent 5 wonderful years between 2014 and 2019. I got my Ph.D. degree from the Department of Automation, Tsinghua University in 2014, under the supervison of Professor Jie Zhou. During my Ph.D. study, I visited the VCLA lab of University of California, Los Angeles (UCLA) between 2012 and 2013, where I worked with Professor Song-Chun Zhu and Professor Ying-Nian Wu. Before that, I got my B.S. degree from the Department of Automation, Tsinghua University in 2009.

Academic Activity

Publication (Google Scholar)

(* Interns, + Equal contribution)

Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation
Hang Gao*+, Xizhou Zhu*+, Steve Lin, and Jifeng Dai
Arxiv Tech Report, 2019.

VL-BERT: Pre-training of Generic Visual-Linguistic Representations
Weijie Su*+, Xizhou Zhu*+, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai
Arxiv Tech Report, 2019.

An Empirical Study of Spatial Attention Mechanisms in Deep Networks
Xizhou Zhu*+, Dazhi Cheng*+, Zheng Zhang+, Steve Lin, and Jifeng Dai
International Conference on Computer Vision (ICCV), 2019.

Deformable ConvNets v2: More Deformable, Better Results
Xizhou Zhu*, Han Hu, Steve Lin, and Jifeng Dai
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
The updated operators utilized in Deformable ConvNets v2 are provided here!

Integrated Object Detection and Tracking with Tracklet-Conditioned Detection
Zheng Zhang+, Dazhi Cheng*+, Xizhou Zhu*+, Steve Lin, and Jifeng Dai
Arxiv Tech Report, 2018.

Towards High Performance Video Object Detection for Mobiles
Xizhou Zhu*, Jifeng Dai, Xingchi Zhu*, Yichen Wei, and Lu Yuan
Arxiv Tech Report, 2018.

Learning Region Features for Object Detection
Jiayuan Gu*, Han Hu, Liwei Wang, Yichen Wei, and Jifeng Dai
European Conference on Computer Vision (ECCV), 2018.

Relation Networks for Object Detection
Han Hu+, Jiayuan Gu*+, Zheng Zhang+, Jifeng Dai, and Yichen Wei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (Oral)
Code is available!

Towards High Performance Video Object Detection
Xizhou Zhu*, Jifeng Dai, Lu Yuan, and Yichen Wei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (Spotlight)

Deformable Convolutional Networks
Jifeng Dai+, Haozhi Qi*+, Yuwen Xiong*+, Yi Li*+, Guodong Zhang*+, Han Hu, and Yichen Wei
International Conference on Computer Vision (ICCV), 2017. (Oral)
Code is available!
Slides of ICCV Oral, COCO2017 workshop

Flow-Guided Feature Aggregation for Video Object Detection
Xizhou Zhu*, Yujie Wang*, Jifeng Dai, Lu Yuan, and Yichen Wei
International Conference on Computer Vision (ICCV), 2017.
Code is available!
Video

Fully Convolutional Instance-aware Semantic Segmentation
Yi Li*+, Haozhi Qi*+, Jifeng Dai, Xiangyang Ji, and Yichen Wei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. (Spotlight)
1-st place winner of the COCO 2016 segmentation challenge
0.24 sec/image test speed (using ResNet-101 net)
Code is available!

Deep Feature Flow for Video Recognition
Xizhou Zhu*, Yuwen Xiong*, Jifeng Dai, Lu Yuan, and Yichen Wei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
Code is available!
Video

R-FCN: Object Detection via Region-based Fully Convolutional Networks
Jifeng Dai, Yi Li, Kaiming He, and Jian Sun
Neural Information Processing Systems (NIPS), 2016.
Code is available!

Instance-sensitive Fully Convolutional Networks
Jifeng Dai, Kaiming He, Yi Li, Shaoqing Ren, and Jian Sun
European Conference on Computer Vision (ECCV), 2016.

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
Di Lin*, Jifeng Dai, Jiaya Jia, Kaiming He, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (Oral)
PASCAL-scribble dataset is available here!

Instance-aware Semantic Segmentation via Multi-task Network Cascades
Jifeng Dai, Kaiming He, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (Oral)
1-st place winner of the COCO 2015 segmentation challenge
0.36 sec/image test speed (using VGG-16 net)
Code is available!

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
Jifeng Dai, Kaiming He, and Jian Sun
International Conference on Computer Vision (ICCV), 2015.

Convolutional Feature Masking for Joint Object and Stuff Segmentation
Jifeng Dai, Kaiming He, and Jian Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.

Generative Modeling of Convolutional Neural Networks
Jifeng Dai, Yang Lu, and Ying-Nian Wu
International Conference on Learning Representations (ICLR), 2015.
project page

Unsupervised Learning of Dictionaries of Hierarchical Compositional Models
Jifeng Dai, Yi Hong, Wenze Hu, Song-Chun Zhu, and Ying-Nian Wu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
project page

Cosegmentation and Cosketch by Unsupervised Learning
Jifeng Dai, Ying-Nian Wu, Jie Zhou, and Song-Chun Zhu
International Conference on Computer Vision (ICCV), 2013.
project page

Mining Sub-categories For Object Detection
Jifeng Dai, Jianjiang Feng, and Jie Zhou
International Conference on Pattern Recognition (ICPR), 2012. (Oral)

Ridge Based Palmprint Matching
Jifeng Dai, Jianjiang Feng, and Jie Zhou
IEEE Biometrics Council Newsletter, 7:4-5, 2013. (Invited paper)

Robust and Efficient Ridge-Based Palmprint Matching
Jifeng Dai, Jianjiang Feng, and Jie Zhou
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 34(8):1618–1632, 2012.

Multi-feature Based High-resolution Palmprint Recognition
Jifeng Dai, and Jie Zhou
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 33(5):945–957, 2011.

Competitions