Researcher profile

Zhihua Wang

Zhihua Wang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Computer Vision eess.IV math.CT math.QA math.RT Artificial Intelligence eess.SP Machine Learning math.GR math.RA

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

10works

0followers

10topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

NTIRE 2026 Challenge on Efficient Low Light Image Enhancement: Methods and Results

This paper presents a comprehensive review of the NITRE 2026 Efficient Low Light Image Enhancement (E-LLIE) Challenge, highlighting the proposed solutions and final outcomes. This challenge focuses on mobile image enhancement under low-light conditions, aiming to design lightweight networks that improve enhancement quality while ensuring practical deployability under limited computational resources. A total of 207 participants registered, 27 teams submitted valid entries, and 17 teams ultimately provided valid factsheet. Based on these submissions, this paper provides a systematic evaluation of recent methods for E-LLIE, offering a comprehensive overview of state-of-the-art progress and demonstrating significant improvements in both performance and efficiency.

preprint2026arXiv

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere

Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods universally depend on large-scale annotations or task-specific training procedures, severely limiting their rapid deployment to novel scenes. We observe that intermediate-layer features of pre-trained multimodal large language models (MLLMs) already encode rich anomaly semantics, yet existing approaches rely on the language output pathway and fail to exploit the geometric discriminability latent in these representations. Based on this finding, we propose SphereVAD, a fully training-free, zero-shot VAD framework that recasts anomaly discrimination as von Mises-Fisher (vMF) likelihood-ratio geodesic inference on the unit hypersphere, unleashing latent discriminability through principled geometric reasoning rather than learning new representations. Specifically, SphereVAD first applies Frechet mean centering to unfold feature distributions and eliminate domain biases, then employs Holistic Scene Attention (HSA) to reinforce feature consistency using cross-video priors, and finally performs vMF-guided Spherical Geodesic Pulling (SGP) to align ambiguous segments with directional prototypes on the spherical manifold. This training-free pipeline requires only minimal synthetic images for calibration. SphereVAD establishes new state-of-the-art results among training-free approaches on three major benchmarks and remains competitive with fully supervised baselines. Code will be available upon acceptance.

preprint2025arXiv

One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training

Rare gastrointestinal lesions are infrequently encountered in routine endoscopy, restricting the data available for developing reliable artificial intelligence (AI) models and training novice clinicians. Here we present EndoRare, a one-shot, retraining-free generative framework that synthesizes diverse, high-fidelity lesion exemplars from a single reference image. By leveraging language-guided concept disentanglement, EndoRare separates pathognomonic lesion features from non-diagnostic attributes, encoding the former into a learnable prototype embedding while varying the latter to ensure diversity. We validated the framework across four rare pathologies (calcifying fibrous tumor, juvenile polyposis syndrome, familial adenomatous polyposis, and Peutz-Jeghers syndrome). Synthetic images were judged clinically plausible by experts and, when used for data augmentation, significantly enhanced downstream AI classifiers, improving the true positive rate at low false-positive rates. Crucially, a blinded reader study demonstrated that novice endoscopists exposed to EndoRare-generated cases achieved a 0.400 increase in recall and a 0.267 increase in precision. These results establish a practical, data-efficient pathway to bridge the rare-disease gap in both computer-aided diagnostics and clinical education.

preprint2024arXiv

Multi-Channel Multi-Domain based Knowledge Distillation Algorithm for Sleep Staging with Single-Channel EEG

This paper proposed a Multi-Channel Multi-Domain (MCMD) based knowledge distillation algorithm for sleep staging using single-channel EEG. Both knowledge from different domains and different channels are learnt in the proposed algorithm, simultaneously. A multi-channel pre-training and single-channel fine-tuning scheme is used in the proposed work. The knowledge from different channels in the source domain is transferred to the single-channel model in the target domain. A pre-trained teacher-student model scheme is used to distill knowledge from the multi-channel teacher model to the single-channel student model combining with output transfer and intermediate feature transfer in the target domain. The proposed algorithm achieves a state-of-the-art single-channel sleep staging accuracy of 86.5%, with only 0.6% deterioration from the state-of-the-art multi-channel model. There is an improvement of 2% compared to the baseline model. The experimental results show that knowledge from multiple domains (different datasets) and multiple channels (e.g. EMG, EOG) could be transferred to single-channel sleep staging.

preprint2022arXiv

Higher Frobenius-Schur indicators for semisimple Hopf algebras in positive characteristic

Let $H$ be a semisimple Hopf algebra over an algebraically closed field $\mathbbm{k}$ of characteristic $p>\dim_{\mathbbm{k}}(H)^{1/2}$. We show that the antipode $S$ of $H$ satisfies the equality $S^2(h)=\mathbf{u}h\mathbf{u}^{-1}$, where $h\in H$, $\mathbf{u}=S(Λ_{(2)})Λ_{(1)}$ and $Λ$ is a nonzero integral of $H$. The formula of $S^2$ enables us to define higher Frobenius-Schur indicators for the Hopf algebra $H$. This generalizes the notions of higher Frobenius-Schur indicators from the case of characteristic 0 to the case of characteristic $p>\dim_{\mathbbm{k}}(H)^{1/2}$. These indicators defined here share some properties with the ones defined over a field of characteristic 0. Especially, all these indicators are gauge invariants for the tensor category Rep$(H)$ of finite dimensional representations of $H$.

preprint2022arXiv

Invariants from the Sweedler power maps on integrals

For a finite-dimensional Hopf algebra $A$ with a nonzero left integral $Λ$, we investigate a relationship between $P_n(Λ)$ and $P_n^J(Λ)$, where $P_n$ and $P_n^J$ are respectively the $n$-th Sweedler power maps of $A$ and the twisted Hopf algebra $A^J$. We use this relation to give several invariants of the representation category Rep$(A)$ considered as a tensor category. As applications, we distinguish the representation categories of 12-dimensional pointed nonsemisimple Hopf algebras. Also, these invariants are sufficient to distinguish the representation categories Rep$(K_8)$, Rep$(\kk Q_8)$ and Rep$(\kk D_4)$, although they have been completely distinguished by their Frobenius-Schur indicators. We further reveal a relationship between the right integrals $λ$ in $A^*$ and $λ^J$ in $(A^J)^*$. This can be used to give a uniform proof of the remarkable result which says that the $n$-th indicator $ν_n(A)$ is a gauge invariant of $A$ for any $n\in \mathbb{Z}$. We also use the expression for $λ^J$ to give an alternative proof of the known result that the Killing form of the Hopf algebra $A$ is invariant under twisting. As a result, the dimension of the Killing radical of $A$ is a gauge invariant of $A$.

preprint2022arXiv

The Grothendieck algebras of certain smash product semisimple Hopf algebras

Let $H$ be a semisimple Hopf algebra over an algebraically closed field $\mathbbm{k}$ of characteristic $p>\dim_{\mathbbm{k}}(H)^{1/2}$ and $p\nmid 2\dim_{\mathbbm{k}}(H)$. In this paper, we consider the smash product semisimple Hopf algebra $H\#\mathbbm{k}G$, where $G$ is a cyclic group of order $n:=2\dim_{\mathbbm{k}}(H)$. Using irreducible representations of $H$ and those of $\mathbbm{k}G$, we determine all non-isomorphic irreducible representations of $H\#\mathbbm{k}G$. There is a close relationship between the Grothendieck algebra $(G_0(H\#\mathbbm{k}G)\otimes_{\mathbb{Z}}\mathbbm{k},*)$ of $H\#\mathbbm{k}G$ and the Grothendieck algebra $(G_0(H)\otimes_{\mathbb{Z}}\mathbbm{k},*)$ of $H$. To establish this connection, we endow with a new multiplication operator $\star$ on $G_0(H)\otimes_{\mathbb{Z}}\mathbbm{k}$ and show that the Grothendieck algebra $(G_0(H\#\mathbbm{k}G)\otimes_{\mathbb{Z}}\mathbbm{k},\ast)$ is isomorphic to the direct sum of $(G_0(H)\otimes_{\mathbb{Z}}\mathbbm{k},*)^{\oplus\frac{n}{2}}$ and $(G_0(H)\otimes_{\mathbb{Z}}\mathbbm{k},\star)^{\oplus\frac{n}{2}}$.

preprint2021arXiv

Fusion categories containing a fusion subcategory with maximal rank

In this paper, we study fusion categories which contain a proper fusion subcategory with maximal rank. They can be viewed as generalizations of near-group fusion categories. We first prove that they admit spherical structure. We then classify those which are non-degenerate or symmetric. Finally, we classify such fusion categories of rank 4.

preprint2020arXiv

A CNN-Based Blind Denoising Method for Endoscopic Images

The quality of images captured by wireless capsule endoscopy (WCE) is key for doctors to diagnose diseases of gastrointestinal (GI) tract. However, there exist many low-quality endoscopic images due to the limited illumination and complex environment in GI tract. After an enhancement process, the severe noise become an unacceptable problem. The noise varies with different cameras, GI tract environments and image enhancement. And the noise model is hard to be obtained. This paper proposes a convolutional blind denoising network for endoscopic images. We apply Deep Image Prior (DIP) method to reconstruct a clean image iteratively using a noisy image without a specific noise model and ground truth. Then we design a blind image quality assessment network based on MobileNet to estimate the quality of the reconstructed images. The estimated quality is used to stop the iterative operation in DIP method. The number of iterations is reduced about 36% by using transfer learning in our DIP process. Experimental results on endoscopic images and real-world noisy images demonstrate the superiority of our proposed method over the state-of-the-art methods in terms of visual quality and quantitative metrics.

preprint2020arXiv

RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Extensive experiments show that our RandLA-Net can process 1 million points in a single pass with up to 200X faster than existing approaches. Moreover, our RandLA-Net clearly surpasses state-of-the-art approaches for semantic segmentation on two large-scale benchmarks Semantic3D and SemanticKITTI.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint