Picture for Xiaojiang Peng

Xiaojiang Peng

Rail Detection: An Efficient Row-based Network and A New Benchmark

Apr 12, 2023
Xinpeng Li, Xiaojiang Peng

Figure 1 for Rail Detection: An Efficient Row-based Network and A New Benchmark

Figure 2 for Rail Detection: An Efficient Row-based Network and A New Benchmark

Figure 3 for Rail Detection: An Efficient Row-based Network and A New Benchmark

Figure 4 for Rail Detection: An Efficient Row-based Network and A New Benchmark

* Accepted by ACMMM 2022

Access Paper or Ask Questions

IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic Segmentation

Dec 06, 2022
Lihua Fu, Haoyue Tian, Xiangping Bryce Zhai, Pan Gao, Xiaojiang Peng

Figure 1 for IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic Segmentation

Figure 2 for IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic Segmentation

Figure 3 for IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic Segmentation

Figure 4 for IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic Segmentation

* Preprint with 8 pages of main body and 3 pages of supplementary material

Access Paper or Ask Questions

AU-Supervised Convolutional Vision Transformers for Synthetic Facial Expression Recognition

Jul 22, 2022
Shuyi Mao, Xinpeng Li, Junyao Chen, Xiaojiang Peng

Figure 1 for AU-Supervised Convolutional Vision Transformers for Synthetic Facial Expression Recognition

Figure 2 for AU-Supervised Convolutional Vision Transformers for Synthetic Facial Expression Recognition

Access Paper or Ask Questions

Video Frame Interpolation Based on Deformable Kernel Region

Apr 25, 2022
Haoyue Tian, Pan Gao, Xiaojiang Peng

Figure 1 for Video Frame Interpolation Based on Deformable Kernel Region

Figure 2 for Video Frame Interpolation Based on Deformable Kernel Region

Figure 3 for Video Frame Interpolation Based on Deformable Kernel Region

Figure 4 for Video Frame Interpolation Based on Deformable Kernel Region

* Accepted to the 31st International Joint Conference on Artificial Intelligence(IJCAI-ECAI 2022)

Access Paper or Ask Questions

Stereo Matching with Cost Volume based Sparse Disparity Propagation

Jan 28, 2022
Wei Xue, Xiaojiang Peng

Figure 1 for Stereo Matching with Cost Volume based Sparse Disparity Propagation

Figure 2 for Stereo Matching with Cost Volume based Sparse Disparity Propagation

Figure 3 for Stereo Matching with Cost Volume based Sparse Disparity Propagation

Figure 4 for Stereo Matching with Cost Volume based Sparse Disparity Propagation

Access Paper or Ask Questions

Spatial and Temporal Networks for Facial Expression Recognition in the Wild Videos

Jul 12, 2021
Shuyi Mao, Xinqi Fan, Xiaojiang Peng

Figure 1 for Spatial and Temporal Networks for Facial Expression Recognition in the Wild Videos

Figure 2 for Spatial and Temporal Networks for Facial Expression Recognition in the Wild Videos

Figure 3 for Spatial and Temporal Networks for Facial Expression Recognition in the Wild Videos

Access Paper or Ask Questions

An Efficient Training Approach for Very Large Scale Face Recognition

Jun 04, 2021
Kai Wang, Shuo Wang, Zhipeng Zhou, Xiaobo Wang, Xiaojiang Peng, Baigui Sun, Hao Li, Yang You

Figure 1 for An Efficient Training Approach for Very Large Scale Face Recognition

Figure 2 for An Efficient Training Approach for Very Large Scale Face Recognition

Figure 3 for An Efficient Training Approach for Very Large Scale Face Recognition

Figure 4 for An Efficient Training Approach for Very Large Scale Face Recognition

* This is a very effcient framework for ultra-large-scale classification tasks. Our code is available at https://github.com/tiandunx/FFC. We will keep updating!

Access Paper or Ask Questions