Bailing Zhang

Bailing Zhang

Auto-generated profile, based on publicly available information

Bailing Zhang

School of Computer Science and Data Engineering, NingboTech University, Ningbo 315100, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 November 2020
Verified
Book Chapter
Closed access
PDF file
FWFangyu Wu
Fangyu Wu
JSJeremy Smith
Jeremy Smith
WLWenjin Lu
Wenjin Lu
CPChaoyi Pang
Chaoyi Pang
BZBailing Zhang
Bailing Zhang

22 August 2022 in IEEE Transactions on Human-Machine Systems
Verified
Journal Article
Closed access
YLYifan Lu
Yifan Lu
GCgenlang chen
genlang chen
CPChaoyi Pang
Chaoyi Pang
Haolan ZhangHaolan Zhang
Haolan Zhang
BZBailing Zhang
Bailing Zhang
3-D human pose estimation or human tracking has always been the focus of research in the human–computer interaction community. As the calibration step of human pose estimation, subject-specific modeling is crucially important to the subsequent pose estimation process. It not only provides a priori knowledge but also clearly defines the tracking target. This article presents a fully automatic subject modeling framework to reconstruct human pose, shape, as well as the body texture in a challenging optimization scenario. By integrating powerful differentiable rendering into the subject-specific modeling pipeline, the proposed method transforms the texture reconstruction problem into analysis by synthesis minimization and solves it efficiently by a gradient-based method. Furthermore, a novel covariance matrix adaptation annealing algorithm is proposed to attack the high-dimensional multimodal optimization problem in an adaptive manner. The domain knowledge of hierarchical human anatomy is seamlessly injected to the annealing optimization process by using a soft covariance matrix mask. All together contributes to the novel algorithm robust to the temptation of local minima. Experiments on the Human3.6 M dataset and the People-Snapshot dataset demonstrate the competitive results to the state of the art both qualitatively and quantitatively.

2 June 2021 in Computer Animation and Virtual Worlds
Verified
Journal Article
Closed access
PDF file
FWFangyu Wu
Fangyu Wu
CPChaoyi Pang
Chaoyi Pang
BZBailing Zhang
Bailing Zhang

19 July 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
FWFangyu Wu
Fangyu Wu
QWQiu-Feng Wang
Qiu-Feng Wang
XLXuan Liu
Xuan Liu
QCQi Chen
Qi Chen
YZYuxuan Zhao
Yuxuan Zhao
Enggee LimEnggee Lim
Enggee Lim

2 February 2024
Verified
Conference Paper
Open access
RWRui Wang
Rui Wang
ZPZhengxin Pan
Zhengxin Pan
FWFangyu Wu
Fangyu Wu
YLYifan Lv
Yifan Lv
BZBailing Zhang
Bailing Zhang
Multi-label classification is a task with diverse applications, but current algorithms heavily rely on accurately labeled data, leading to time-consuming and labor-intensive data collection. However, multi-label classification with partial labels presents significant challenges. In this study, we propose Multi-modal Contextual Prompt Learning (MCPL), a novel approach that leverages large-scale visual-language models and exploits the strong image-text alignment in CLIP to address the scarcity of label annotations. We pre-train the visual language model’s encoder on a large number of image-text pairs.. We introduce multi-modal contextual prompt learning in both images and labeled text to better utilize the image-label correspondence within CLIP, resulting in enhanced multi-label classification performance, even when faced with partial labels. We also use the coupling function to couple the two modes and realize the interactive connection of the two modal prompts. Extensive experiments on the MS-COCO and VOC2007 datasets, demonstrating its superiority and achieving competitive performance.