Ke Zhang

Prof. Ke Zhang


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
QZQuan Zhang
Quan Zhang
YQYuxin Qi
Yuxin Qi
XTXi Tang
Xi Tang
RYRui Yuan
Rui Yuan
XLXi Lin
Xi Lin
YCYuan Chun
Yuan Chun
Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the fully-supervised detection head. We argue that the noise in pseudo-labels would interfere with the learning of fully-supervised detection head, leading to significant performance leakage. Issues with noisy labels include:(1) inaccurate boundary localization; (2) undetected short action clips; (3) multiple adjacent segments incorrectly detected as one segment. To target these issues, we introduce a two-stage noisy label learning strategy to harness every potential useful signal in noisy labels. First, we propose a frame-level pseudo-label generation model with a context-aware denoising algorithm to refine the boundaries. Second, we introduce an online-revised teacher-student framework with a missing instance compensation module and an ambiguous instance correction module to solve the short-action-missing and many-to-one problems. Besides, we apply a high-quality pseudo-label mining loss in our online-revised teacher-student framework to add different weights to the noisy labels to train more effectively. Our model outperforms the previous state-of-the-art method in detection accuracy and inference speed greatly upon the THUMOS14 and ActivityNet v1.2 benchmarks.



30 December 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
ZCZilei Chen
Zilei Chen
YLYuyue Lou
Yuyue Lou
KZKe Zhang
Ke Zhang
Electroencephalography (EEG) is widely used in brain–computer interfaces and clinical diagnosis, yet its low amplitude makes it highly vulnerable to artifacts that degrade downstream analysis. Existing EEG denoising approaches can be broadly grouped into two paradigms: (i) data-driven denoising methods that explicitly separate and remove noise components, and (ii) feature-learning methods that seek noise-robust latent representations directly from raw signals. This survey reviews recent progress in both paradigms, with a particular focus on integrating classical signal-processing principles with self-supervised learning (SSL). We argue that such integration can improve denoising effectiveness while enhancing interpretability and robustness under cross-subject, cross-device, and low signal-to-noise ratio (SNR) conditions. Specifically, we summarize representative techniques and their assumptions, propose a two-level taxonomy organized by denoising logic and technical paradigm, and provide supplementary experiments that benchmark traditional denoising modules within large EEG modeling pipelines. We further summarize practitioner-oriented guidelines to facilitate task- and data-adaptive preprocessing--SSL pipeline selection. Finally, we discuss open challenges and future directions toward hybrid denoising frameworks that combine signal-processing priors with deep neural networks.

27 February 2025 in arXiv
Verified
Preprint
Open access
PDF file
TYTianle Yang
Tianle Yang
LCLuyao Chang
Luyao Chang
JYJiadong Yan
Jiadong Yan
JLJuntao Li
Juntao Li
ZWZhi Wang
Zhi Wang
KZKe Zhang
Ke Zhang
As industrial products become abundant and sophisticated, visual industrial defect detection receives much attention, including two-dimensional and three-dimensional visual feature modeling. Traditional methods use statistical analysis, abnormal data synthesis modeling, and generation-based models to separate product defect features and complete defect detection. Recently, the emergence of foundation models has brought visual and textual semantic prior knowledge. Many methods are based on foundation models (FM) to improve the accuracy of detection, but at the same time, increase model complexity and slow down inference speed. Some FM-based methods have begun to explore lightweight modeling ways, which have gradually attracted attention and deserve to be systematically analyzed. In this paper, we conduct a systematic survey with comparisons and discussions of foundation model methods from different aspects and briefly review non-foundation model (NFM) methods recently published. Furthermore, we discuss the differences between FM and NFM methods from training objectives, model structure and scale, model performance, and potential directions for future exploration. Through comparison, we find FM methods are more suitable for few-shot and zero-shot learning, which are more in line with actual industrial application scenarios and worthy of in-depth research.

10 July 2025 in arXiv
Verified
Preprint
Open access
PDF file
WYWei Yao
Wei Yao
SXShuzhao Xie
Shuzhao Xie
LLLetian Li
Letian Li
WZWeixiang Zhang
Weixiang Zhang
ZLZhixin Lai
Zhixin Lai
ZWZhi Wang
Zhi Wang
Current 4D Gaussian frameworks for dynamic scene reconstruction deliver impressive visual fidelity and rendering speed, however, the inherent trade-off between storage costs and the ability to characterize complex physical motions significantly limits the practical application of these methods. To tackle these problems, we propose SD-GS, a compact and efficient dynamic Gaussian splatting framework for complex dynamic scene reconstruction, featuring two key contributions. First, we introduce a deformable anchor grid, a hierarchical and memory-efficient scene representation where each anchor point derives multiple 3D Gaussians in its local spatiotemporal region and serves as the geometric backbone of the 3D scene. Second, to enhance modeling capability for complex motions, we present a deformation-aware densification strategy that adaptively grows anchors in under-reconstructed high-dynamic regions while reducing redundancy in static areas, achieving superior visual quality with fewer anchors. Experimental results demonstrate that, compared to state-of-the-art methods, SD-GS achieves an average of 60\% reduction in model size and an average of 100\% improvement in FPS, significantly enhancing computational efficiency while maintaining or even surpassing visual quality.