no code implementations • 24 May 2022 • Mingzhe Sui, Hanting Li, Zhaoqing Zhu, Feng Zhao
2D+3D facial expression recognition (FER) can effectively cope with illumination changes and pose variations by simultaneously merging 2D texture and more robust 3D depth information.
no code implementations • 25 Apr 2022 • Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinhong Jiang, Feng Zhao
3D object detection from multiple image views is a fundamental and challenging task for visual scene understanding.
1 code implementation • 3 Feb 2022 • Guangkai Xu, Wei Yin, Hao Chen, Kai Cheng, Feng Zhao, Chunhua Shen
However, in some video-based scenarios such as video depth estimation and 3D scene reconstruction from a video, the unknown scale and shift residing in per-frame prediction may cause the depth inconsistency.
no code implementations • 17 Jan 2022 • Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinghong Jiang, Feng Zhao, Bolei Zhou, Hang Zhao
This map enables our model to automate the alignment of non-homogenous features in a dynamic and data-driven manner.
no code implementations • 14 Jan 2022 • Hanting Li, Mingzhe Sui, Zhaoqing Zhu, Feng Zhao
By adding the position embeddings of the face generated by PC module at the end of the two branches, the PC module can help to add position information to facial muscle motion pattern features for the MER.
1 code implementation • 1 Dec 2021 • Zizheng Yang, Xin Jin, Kecheng Zheng, Feng Zhao
During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images.
no code implementations • NeurIPS Workshop DLDE 2021 • Feng Zhao, Xiang Chen, Jun Wang, Zuoqiang Shi, Shao-Lun Huang
Traditionally, we provide technical parameters for ODE solvers, such as the order, the stepsize and the local error threshold.
no code implementations • 20 Sep 2021 • Hanting Li, Mingzhe Sui, Zhaoqing Zhu, Feng Zhao
To the best of our knowledge, this is the first work to introduce vision transformer into multimodal 2D+3D FER.
1 code implementation • 7 Jul 2021 • Zehui Chen, Chenhongyi Yang, Qiaofei Li, Feng Zhao, Zheng-Jun Zha, Feng Wu
Extensive experiments on MS COCO benchmark show that our approach can lead to 2. 0 mAP, 2. 4 mAP and 2. 2 mAP absolute improvements on RetinaNet, FCOS, and ATSS baselines with negligible extra overhead.
no code implementations • 8 Jun 2021 • Hanting Li, Mingzhe Sui, Feng Zhao, ZhengJun Zha, Feng Wu
Facial Expression Recognition (FER) in the wild is an extremely challenging task in computer vision due to variant backgrounds, low-quality facial images, and the subjectiveness of annotators.
1 code implementation • 10 Sep 2020 • Zehui Chen, Qiaofei Li, Feng Zhao
This technical report introduces our solutions of Team 'FineGrainedSeg' for Instance Segmentation track in 3D AI Challenge 2020.
2 code implementations • CVPR 2020 • Haozhe Qi, Chen Feng, Zhiguo Cao, Feng Zhao, Yang Xiao
Specifically, we first sample seeds from the point clouds in template and search area respectively.
no code implementations • 6 Nov 2013 • Feng Zhao
The thesis is aimed to solve the template-free protein folding problem by tackling two important components: efficient sampling in vast conformation space, and design of knowledge-based potentials with high accuracy.