Search

Your search keyword '"Liu, Bingkun"' showing total 233 results
Start Over Author "Liu, Bingkun"
233 results on '"Liu, Bingkun"'

11. Few-Shot Model Adaptation for Customized Facial Landmark Detection, Segmentation, Stylization and Shadow Removal

Author

Wei, Zhen, Liu, Bingkun, Wang, Weinong, and Tai, Yu-Wing

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Despite excellent progress has been made, the performance of deep learning based algorithms still heavily rely on specific datasets, which are difficult to extend due to labor-intensive labeling. Moreover, because of the advancement of new applications, initial definition of data annotations might not always meet the requirements of new functionalities. Thus, there is always a great demand in customized data annotations. To address the above issues, we propose the Few-Shot Model Adaptation (FSMA) framework and demonstrate its potential on several important tasks on Faces. The FSMA first acquires robust facial image embeddings by training an adversarial auto-encoder using large-scale unlabeled data. Then the model is equipped with feature adaptation and fusion layers, and adapts to the target task efficiently using a minimal amount of annotated images. The FSMA framework is prominent in its versatility across a wide range of facial image applications. The FSMA achieves state-of-the-art few-shot landmark detection performance and it offers satisfying solutions for few-shot face segmentation, stylization and facial shadow removal tasks for the first time., Comment: with supplementary file

Published
2021

43. End-to-End RoboticArmVision Servo Research Combined with Bottleneck Attention Mechanism.

Author

LIU Bingkun, PI Jiatian, and XU Jin

Subjects
FEATURE extraction, CONVOLUTIONAL neural networks, ANGULAR velocity, LINEAR velocity, DATA mining, BOTTLENECKS (Manufacturing), INFORMATION networks
Abstract

Aiming at the cumbersome feature extraction steps and poor real-time performance of traditional visual servoing algorithms, an end-to-end direct visual servoing algorithm based on convolutional neural network is proposed. By directly predicting the instantaneous linear velocity and instantaneous angular velocity of the camera installed at the end of the robotic arm, servo positioning works without the need to label handcrafted features, camera intrinsics, or depth information. Firstly, the image observed by the camera is input into the GhostNet feature extraction network for information extraction, and the bottleneck attention module (BAM) is integrated into the network to enhance the spatial information and channel information of the target object. Then, the fully connected layer is used as the speed regression function, the linear velocity and angular velocity are decoupled and regressed. Finally, a real-time capture method is used to create the dataset required for training in the real environment, and the velocity labels are generated according to the position-based visual servo control law algorithm. Efficient and accurate localization and tracking tasks are accomplished under the trained initial pose. The experimental test results in a large number of real scenes verify the effectiveness of the algorithm, and it is also robust to scene background information. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

47. Optical Fiber Fabry-Perot Humidity Sensor Based on BPQDs-PVA Sandwiched in SMF

Author

Shao, Min, Liu, Bingkun, Wang, Yanmei, Liu, Yinggang, and Qiao, Xueguang

Abstract

An optical fiber humidity sensor based on filmy black phosphorus quantum dots- polyvinyl alcohol (BPQDs-PVA) gel sandwiched between two sections of single-mode fibers (SMFs) is proposed. The BPQDs-PVA compound serves as Fabry-Perot (FP) cavity that directly perceives external humidity variations and modulates the reflection spectrum. Based on the excellent hygroscopicity of BPQDs-PVA compound, the humidity sensor achieved a humidity sensitivity of 0.2259 nm/%RH in the range of 42–57 %RH, and an ultra-high humidity sensitivity of 12.4307 nm/%RH in the range of 57–60 %RH. The maximum instability of the sensor is 0.02 %RH, and the response/recovery time are 0.78s/1.24s, respectively. Easy fabrication process, low cost, good stability and high sensitivity make it has great potential in fields which need accurate humidity monitor and control.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results