37 citations · 47 across the 6 of their papers we have counts for
6 papers
EFormer: Enhanced Transformer towards Semantic-Contour Features of Foreground for Portraits Matting
Zitao Wang, Qiguang Miao, Peipei Zhao +1
The portrait matting task aims to extract an alpha matte with complete semantics and finely-detailed contours. In comparison to CNN-based approaches, transformers with self-attenti…
One-Nearest Neighborhood Guides Inlier Estimation for Unsupervised Point Cloud Registration
Yongzhe Yuan, Yue Wu, Maoguo Gong +2
The precision of unsupervised point cloud registration methods is typically limited by the lack of reliable inlier estimation and self-supervised signal, especially in partially ov…
Evolutionary Multitasking with Solution Space Cutting for Point Cloud Registration
Wu Yue, Peiran Gong, Maoguo Gong +5
Point cloud registration (PCR) is a popular research topic in computer vision. Recently, the registration method in an evolutionary way has received continuous attention because of…
Multi-view Point Cloud Registration based on Evolutionary Multitasking with Bi-Channel Knowledge Sharing Mechanism
Yue Wu, Yibo Liu, Maoguo Gong +5
Multi-view point cloud registration is fundamental in 3D reconstruction. Since there are close connections between point clouds captured from different viewpoints, registration per…
Scene Graph Generation: A Comprehensive Survey
Guangming Zhu, Liang Zhang, Youliang Jiang +8
Deep learning techniques have led to remarkable breakthroughs in the field of generic object detection and have spawned a lot of scene-understanding tasks in recent years. Scene gr…
ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition
Jun Wan, Chi Lin, Longyin Wen +7
The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and I…