High Performance Visual Tracking with Siamese Region Proposal Network
- Bo Li, Junjie Yan, Wei Wu, Zheng Zhu, Xiaolin Hu
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 1 June 2018
The Siamese region proposal network (Siamese-RPN) is proposed which is end-to-end trained off-line with large-scale image pairs for visual object tracking and consists of SiAMESe subnetwork for feature extraction and region proposal subnetwork including the classification branch and regression branch.
SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks
- Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan
- Computer ScienceComputer Vision and Pattern Recognition
- 31 December 2018
This work proves the core reason Siamese trackers still have accuracy gap comes from the lack of strict translation invariance, and proposes a new model architecture to perform depth-wise and layer-wise aggregations, which not only improves the accuracy but also reduces the model size.
A face antispoofing database with diverse attacks
- Zhiwei Zhang, Junjie Yan, Sifei Liu, Zhen Lei, Dong Yi, S. Li
- Computer ScienceInternational Conference on Biometrics
- 6 August 2012
A face antispoofing database which covers a diverse range of potential attack variations, and a baseline algorithm is given for comparison, which explores the high frequency information in the facial region to determine the liveness.
Distractor-aware Siamese Networks for Visual Object Tracking
- Zheng Zhu, Qiang Wang, Bo Li, Wei Wu, Junjie Yan, Weiming Hu
- Computer ScienceEuropean Conference on Computer Vision
- 18 August 2018
This paper focuses on learning distractor-aware Siamese networks for accurate and long-term tracking, and extends the proposed approach for long- term tracking by introducing a simple yet effective local-to-global search region strategy.
Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion
- Haiyu Zhao, Maoqing Tian, Xiaoou Tang
- Computer ScienceComputer Vision and Pattern Recognition
- 1 July 2017
This study proposes a novel Convolutional Neural Network, called Spindle Net, based on human body region guided multi-stage feature decomposition and tree-structured competitive feature fusion, which is the first time human body structure information is considered in a CNN framework to facilitate feature learning.
HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
- Xihui Liu, Haiyu Zhao, Xiaogang Wang
- Computer ScienceIEEE International Conference on Computer Vision
- 28 September 2017
A new attentionbased deep neural network, named as HydraPlus-Net (HPnet), that multi-directionally feeds the multi-level attention maps to different feature layers to enrich the final feature representations for a pedestrian image.
Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift
- Ruijia Xu, Ziliang Chen, W. Zuo, Junjie Yan, Liang Lin
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 2 March 2018
This paper proposes a deep cocktail network (DCTN) to battle the domain and category shifts among multiple sources and evaluates DCTN in three domain adaptation benchmarks, which clearly demonstrate the superiority of the framework.
FOTS: Fast Oriented Text Spotting with a Unified Network
- Xuebo Liu, Ding Liang, Shipeng Yan, Dagui Chen, Y. Qiao, Junjie Yan
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 5 January 2018
This work proposes a unified end-to-end trainable Fast Oriented Text Spotting (FOTS) network for simultaneous detection and recognition, sharing computation and visual information among the two complementary tasks, and introduces RoIRotate to share convolutional features between detection and Recognition.
High-fidelity Pose and Expression Normalization for face recognition in the wild
- Xiangyu Zhu, Zhen Lei, Junjie Yan, Dong Yi, S. Li
- Computer ScienceComputer Vision and Pattern Recognition
- 7 June 2015
A High-fidelity Pose and Expression Normalization (HPEN) method with 3D Morphable Model (3DMM) which can automatically generate a natural face image in frontal pose and neutral expression and an inpainting method based on Possion Editing to fill the invisible region caused by self occlusion is proposed.
Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification
- Zhongdao Wang, Luming Tang, Xiaogang Wang
- Computer ScienceIEEE International Conference on Computer Vision
- 1 October 2017
Both the orientation invariant feature embedding and the spatio-temporal regularization achieve considerable improvements in the vehicle Re-identification problem.
...
...