Author name cluster

Zhaowen Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

JBHI Journal 2026 Journal Article

Sleep Stage Specificity to Window Length Variations: A Decision Fusion Strategy for Enhanced Scoring

Zhaowen Wang
Dongdong Zhou
Qi Xu
Fengyu Cong
Mohammad Al-Sa'd
Jenni Raitoharju

Sleep stage scoring is a fundamental component of sleep medicine, enabling a comprehensive assessment of sleep architecture and quality. While the standard 30-second (30s) epoch defined by the American Academy of Sleep Medicine represents the clinical gold standard, most automatic sleep stage scoring algorithms process these fixed segments in isolation. This approach may hinder the detection of transient arousal events, sleep spindles, K-complexes, and other phasic sleep characteristics that occur on finer timescales, thus necessitating analysis at sub-epoch resolution. To leverage complementary information across temporal scales, we propose a Multi-scale Decision Fusion Sleep Network (MDFSleepNet). Our systematic analysis across window lengths (1-30 seconds) reveals significant stage-specific temporal preferences: N1 and N3 stages achieve higher accuracy with 30s windows capturing comprehensive context, while N2 stage classification benefits markedly from shorter windows (1-2 seconds) optimized for transient micro-structure detection. REM stage preferences exhibit dataset variability. Motivated by these findings, MDFSleepNet integrates these complementary scales through a dual-stream architecture combining multi-scale segmentation, scale-specific feature learning, and cross-scale fusion. Evaluated on ISRUC-S1 and ISRUC-S3 (by fusing 5s and 30s windows), MDFSleepNet achieves state-of-the-art accuracies of 83. 5% and 84. 8% (Cohen's Kappa: 0. 786, 0. 804). On Sleep-EDF-20 (fusing 15s and 30s windows), it reaches 90. 9% accuracy (Cohen's Kappa: 0. 875), demonstrating robust performance through complementary multi-scale fusion. The source code for this study is publicly available at https://github.com/wzw999/MDFSleepNet.

Details DOI

TMLR Journal 2024 Journal Article

Improving Diffusion Models for Scene Text Editing with Dual Encoders

Jiabao Ji
Guanhua Zhang
Zhaowen Wang
Bairu Hou
Zhifei Zhang
Brian L. Price
Shiyu Chang

Scene text editing is a challenging task that involves modifying or inserting specified texts in an image while maintaining its natural and realistic appearance. Most previous approaches to this task rely on style-transfer models that crop out text regions and feed them into image transfer models, such as GANs. However, these methods are limited in their ability to change text style and are unable to insert texts into images. Recent advances in diffusion models have shown promise in overcoming these limitations with text-conditional image editing. However, our empirical analysis reveals that state-of-the-art diffusion models struggle with rendering correct text and controlling text style. To address these problems, we propose DIFFSTE to improve pre-trained diffusion models with a dual encoder design, which includes a character encoder for better text legibility and an instruction encoder for better style control. An instruction tuning framework is introduced to train our model to learn the mapping from the text instruction to the corresponding image with either the specified style or the style of the surrounding texts in the background. Such a training method further brings our method the zero-shot generalization ability to the following three scenarios: generating text with unseen font variation, e.g., italic and bold, mixing different fonts to construct a new font, and using more relaxed forms of natural language as the instructions to guide the generation task. We evaluate our approach on five datasets and demonstrate its superior performance in terms of text correctness, image naturalness, and style controllability.

PDF Details

AAAI Conference 2023 Conference Paper

Layout Representation Learning with Spatial and Structural Hierarchies

Yue Bai
Dipu Manandhar
Zhaowen Wang
John Collomosse
Yun Fu

We present a novel hierarchical modeling method for layout representation learning, the core of design documents (e.g., user interface, poster, template). Existing works on layout representation often ignore element hierarchies, which is an important facet of layouts, and mainly rely on the spatial bounding boxes for feature extraction. This paper proposes a Spatial-Structural Hierarchical Auto-Encoder (SSH-AE) that learns hierarchical representation by treating a hierarchically annotated layout as a tree format. On the one side, we model SSH-AE from both spatial (semantic views) and structural (organization and relationships) perspectives, which are two complementary aspects to represent a layout. On the other side, the semantic/geometric properties are associated at multiple resolutions/granularities, naturally handling complex layouts. Our learned representations are used for effective layout search from both spatial and structural similarity perspectives. We also newly involve the tree-edit distance (TED) as an evaluation metric to construct a comprehensive evaluation protocol for layout similarity assessment, which benefits a systematic and customized layout search. We further present a new dataset of POSTER layouts which we believe will be useful for future layout research. We show that our proposed SSH-AE outperforms the existing methods achieving state-of-the-art performance on two benchmark datasets. Code is available at github.com/yueb17/SSH-AE.

PDF Details DOI

NeurIPS Conference 2021 Conference Paper

A Multi-Implicit Neural Representation for Fonts

Pradyumna Reddy
Zhifei Zhang
Zhaowen Wang
Matthew Fisher
Hailin Jin
Niloy Mitra

Fonts are ubiquitous across documents and come in a variety of styles. They are either represented in a native vector format or rasterized to produce fixed resolution images. In the first case, the non-standard representation prevents benefiting from latest network architectures for neural representations; while, in the latter case, the rasterized representation, when encoded via networks, results in loss of data fidelity, as font-specific discontinuities like edges and corners are difficult to represent using neural networks. Based on the observation that complex fonts can be represented by a superposition of a set of simpler occupancy functions, we introduce multi-implicits to represent fonts as a permutation-invariant set of learned implict functions, without losing features (e. g. , edges and corners). However, while multi-implicits locally preserve font features, obtaining supervision in the form of ground truth multi-channel signals is a problem in itself. Instead, we propose how to train such a representation with only local supervision, while the proposed neural architecture directly finds globally consistent multi-implicits for font families. We extensively evaluate the proposed representation for various tasks including reconstruction, interpolation, and synthesis to demonstrate clear advantages with existing alternatives. Additionally, the representation naturally enables glyph completion, wherein a single characteristic font is used to synthesize a whole font family in the target style.

PDF Details

IJCAI Conference 2019 Conference Paper

Adversarial Graph Embedding for Ensemble Clustering

Zhiqiang Tao
Hongfu Liu
Jun Li
Zhaowen Wang
Yun Fu

Ensemble clustering generally integrates basic partitions into a consensus one through a graph partitioning method, which, however, has two limitations: 1) it neglects to reuse original features; 2) obtaining consensus partition with learnable graph representations is still under-explored. In this paper, we propose a novel Adversarial Graph Auto-Encoders (AGAE) model to incorporate ensemble clustering into a deep graph embedding process. Specifically, graph convolutional network is adopted as probabilistic encoder to jointly integrate the information from feature content and consensus graph, and a simple inner product layer is used as decoder to reconstruct graph with the encoded latent variables (i. e. , embedding representations). Moreover, we develop an adversarial regularizer to guide the network training with an adaptive partition-dependent prior. Experiments on eight real-world datasets are presented to show the effectiveness of AGAE over several state-of-the-art deep embedding and ensemble clustering methods.

PDF Details

NeurIPS Conference 2017 Conference Paper

Universal Style Transfer via Feature Transforms

Yijun Li
Chen Fang
Jimei Yang
Zhaowen Wang
Xin Lu
Ming-Hsuan Yang

Universal style transfer aims to transfer arbitrary visual styles to content images. Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen styles or compromised visual quality. In this paper, we present a simple yet effective method that tackles these limitations without training on any pre-defined styles. The key ingredient of our method is a pair of feature transforms, whitening and coloring, that are embedded to an image reconstruction network. The whitening and coloring transforms reflect direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural style transfer. We demonstrate the effectiveness of our algorithm by generating high-quality stylized images with comparisons to a number of recent methods. We also analyze our method by visualizing the whitened features and synthesizing textures by simple feature coloring.

PDF Details

AAAI Conference 2016 Conference Paper

Epitomic Image Super-Resolution

Yingzhen Yang
Zhangyang Wang
Zhaowen Wang
Shiyu Chang
Ding Liu
Honghui Shi
Thomas Huang

We propose Epitomic Image Super-Resolution (ESR) to enhance the current internal SR methods that exploit the selfsimilarities in the input. Instead of local nearest neighbor patch matching used in most existing internal SR methods, ESR employs epitomic patch matching that features robustness to noise, and both local and non-local patch matching. Extensive objective and subjective evaluation demonstrate the effectiveness and advantage of ESR on various images.

PDF Details