Multi-stage Progressive Reasoning for Dunhuang Murals Inpainting

no code implementations • 10 May 2023 • Wenjie Liu, Baokai Liu, Shiqiang Du, Yuqing Shi, Jiacheng Li, Jianhua Wang

The execution of the model is similar to the process of a mural restorer (i. e., inpainting the structure of the damaged mural globally first and then adding the local texture details further).

Image Inpainting

Preventing Dimensional Collapse of Incomplete Multi-View Clustering via Direct Contrastive Learning

no code implementations • 22 Mar 2023 • Kaiwu Zhang, Shiqiang Du, Baokai Liu, Shengxia Gao

2) The recovered view contain inconsistent private information and useless private information will mislead the learning of common semantics due to consistent learning and reconstruction learning on the same feature.

Clustering Contrastive Learning +2

An advanced YOLOv3 method for small object detection

no code implementations • 6 Dec 2022 • Baokai Liu, Fengjie He, Shiqiang Du, Jiacheng Li, Wenjie Liu

Small object detection has important application value in the fields of autonomous driving and drone scene analysis.

Autonomous Driving Object +2

Dunhuang murals contour generation network based on convolution and self-attention fusion

no code implementations • 2 Dec 2022 • Baokai Liu, Fengjie He, Shiqiang Du, Kaiwu Zhang, Jianhua Wang

Compared with existing methods, it is shown on different public datasets that our method is able to generate sharper and richer edge maps.

Cultural Vocal Bursts Intensity Prediction Edge Detection