no code implementations • 18 Sep 2023 • XiaoFeng Wang, Zheng Zhu, Guan Huang, Xinze Chen, Jiagang Zhu, Jiwen Lu
The established world model holds immense potential for the generation of high-quality driving videos, and driving policies for safe maneuvering.
no code implementations • 21 Apr 2022 • Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Dalong Du, Jiwen Lu, Jie zhou
For a comprehensive evaluation of face matchers, three recognition tasks are performed under standard, masked and unbiased settings, respectively.
no code implementations • 10 Sep 2021 • Yunze Chen, JunJie Huang, Jiagang Zhu, Zheng Zhu, Tian Yang, Guan Huang, Dalong Du
The current research on this problem mainly focuses on designing an efficient Fully-connected layer (FC) to reduce GPU memory consumption caused by a large number of identities.
no code implementations • 16 Aug 2021 • Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Jia Guo, Jiwen Lu, Dalong Du, Jie zhou
There are second phase of the challenge till October 1, 2021 and on-going leaderboard.
no code implementations • CVPR 2021 • Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Jiwen Lu, Dalong Du, Jie zhou
In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol.
Ranked #1 on Face Verification on IJB-C (training dataset metric)
no code implementations • 17 Dec 2020 • Pengju Zhang, Yihong Wu, Jiagang Zhu
In this paper, we propose a Semi-Global Shape-aware Network (SGSNet) considering both feature similarity and proximity for preserving object shapes when modeling long-range dependencies.
no code implementations • 27 Feb 2019 • Yiming Hu, Jianquan Li, Xianlei Long, Shenhua Hu, Jiagang Zhu, Xingang Wang, Qingyi Gu
Deep neural networks (DNNs) have achieved great success in a wide range of computer vision areas, but the applications to mobile devices is limited due to their high storage and computational cost.
no code implementations • 27 Feb 2019 • Yiming Hu, Siyang Sun, Jianquan Li, Jiagang Zhu, Xingang Wang, Qingyi Gu
Particularly, we introduce an additional loss to encode the differences in the feature and semantic distributions within feature maps between the baseline model and the pruned one.
no code implementations • 14 Dec 2018 • Jiagang Zhu, Wei Zou, Liang Xu, Yiming Hu, Zheng Zhu, Manyu Chang, Jun-Jie Huang, Guan Huang, Dalong Du
On NTU RGB-D, Action Machine achieves the state-of-the-art performance with top-1 accuracies of 97. 2% and 94. 3% on cross-view and cross-subject respectively.
Ranked #1 on Action Recognition on UTD-MHAD
no code implementations • 18 Nov 2018 • Junjie Huang, Wei Zou, Zheng Zhu, Jiagang Zhu
Obtained by moving object detection, the foreground mask result is unshaped and can not be directly used in most subsequent processes.
no code implementations • 18 Nov 2018 • Junjie Huang, Wei Zou, Zheng Zhu, Jiagang Zhu
Real-time motion detection in non-stationary scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource.
Motion Detection Motion Detection In Non-Stationary Scenes +1
no code implementations • 13 Jul 2018 • Junjie Huang, Wei Zou, Jiagang Zhu, Zheng Zhu
Real-time moving object detection in unconstrained scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource.
1 code implementation • 11 Nov 2017 • Jiagang Zhu, Wei Zou, Zheng Zhu
From the frame/clip-level feature learning to the video-level representation building, deep learning methods in action recognition have developed rapidly in recent years.
1 code implementation • 12 Sep 2017 • Jiagang Zhu, Wei Zou, Zheng Zhu
For the two-stream style methods in action recognition, fusing the two streams' predictions is always by the weighted averaging scheme.