Chunlei Wu

EDBT 2026 Demo / reviewers in the wild / expert

dblp:78/4773 · DBLP profile ↗

← Back

49ranked-venue papers

10as first author

40since 2021 · last 2026

—ORCID · conflict

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 21 · 7 first-author · 19 since 2021Applied, interdisciplinary, general and emerging computing · 18 · 2 first-author · 13 since 2021Graphics, computer vision, multimedia, augmented reality and games · 11 · 1 first-author · 10 since 2021Databases, data management, data science and information retrieval · 1

Year	Publication	Venue	Position
2026	AGPL-KEM : Attribute-guided prompt learning with knowledge experts mixture for few-shot remote sensing image classification Chunlei Wu, Congzheng Zhu, Qinfu Xu, Yongzhen Zhang, Leiquan Wang, Jie Wu 0033	Knowl. Based Syst.	1
2026	A memory-tree driven network for multi-view fusion anomaly detection Chunlei Wu, Huan Zhang 0015, Leiquan Wang	Pattern Recognit.	2
2026	Reconstruction error-aware collaborative memory network for unsupervised anomaly detection Chunlei Wu, Huan Zhang 0015, Leiquan Wang	Pattern Recognit.	2
2025	Towards Multimodal Sentiment Analysis via Hierarchical Correlation Modeling with Semantic Distribution Constraints abstract Sentiment analysis is rapidly advancing by utilizing various data modalities (e.g., text, video, and audio). However, most existing techniques only learn the atomic-level features that reflect strong correlations, while ignoring more complex compositions in multimodal data. Moreover, they also neglected the incongruity in semantic distribution among modalities. In light of this, we introduce a novel Hierarchical Correlation Modeling Network (HCMNet), which enhances the multimodal sentiment analysis by exploring both the atomic-level correlations based on dynamic attention reasoning and the composition-level correlations through topological graph reasoning. In addition, we also alleviate the impact of distributional inconsistencies between modalities from both atomic-level and composition-level perspectives. Specifically, we first design an atomic-level contrastive loss that constrains the semantic distribution across modalities to mitigate the atomic-level inconsistency. Then, we design a graph optimal transport module that integrates transport flows with different graphs to constrain the composition-level semantic distribution, thus reducing the inconsistency of compositional nodes. Experiments on three public benchmark datasets have demonstrated the superiority of the proposed model over the state-of-the-art methods. Qinfu Xu, Chunlei Wu, Leiquan Wang, Shaozu Yuan, Jie Wu 0033, Jing Lu 0013, Hengyang Zhou	AAAI	3
2025	Multiple Feature Refining Network for Visual Emotion Distribution Learning abstract The significance of visual emotion distribution learning (VEDL) has surged, particularly with the growing inclination to convey emotions through images. The key of VEDL lies in capturing both low- and high-level features within the same visual content, thus promoting the model for salient and subtle emotion awareness. To learn the distribution of emotions involved in images, most previous works learn coarse semantic knowledge with unbiased filtering. Consequently, they focus on the entire scene and suffer from the redundancy of semantic-irrelevant information, which diminishes the affective coherence, impeding the comprehension of emotional attributes within the treated features. In light of this, we reanalyze from the perspective of information filtering and propose a novel method called Multiple Feature Refining Network (MFRN). To minimize low-level feature redundancy, we design a wavelet-based separated frequency modeling, named Spectral Mixer, to learn invariant representations and enhance emotion saliency in low-level image features. At the higher semantic level, we design a Semantic Graph Prompt Learning for emotional semantic filtering, ensuring the purity of emotional information and providing the model with richer content semantics. Experiments conducted on three commonly used datasets have demonstrated the superiority of our MFRN model over cutting-edge methods. Qinfu Xu, Shaozu Yuan, Jie Wu 0033, Leiquan Wang, Chunlei Wu	AAAI	6
2025	From Subtle Hints to Grand Expressions - Mastering Fine-grained Emotions with Dynamic Multimodal Analysis abstract Multimodal Emotion Analysis (MEA) plays a crucial role in extracting and understanding emotional insights from diverse data sources, including text, video, and audio. However, existing methods may overlook the key issue that multimodal components exhibit asynchronism temporally and they obtain insufficient representation of fine-grained emotional expressions. In light of this, we propose a unified emotion reasoning model, EmoChat, which enhances multimodal emotion analysis by dynamically generating emotion-related tokens and fine-grained expression information through facial action modeling. To incorporate expression semantics, we design the AU Agent, a lightweight facial expression extractor, to provide LLMs with fine-grained facial knowledge for reasoning. In addition, we propose the Correlation Aggregator to alleviate the correlation differences between acoustic features and textual content. Therefore, our method decouples both the audio and vision modalities, allowing for efficient token-level emotion cues mining in misaligned multimodal input, while maintaining semantic consistency across different languages. Experiments on public benchmark datasets have demonstrated the superiority of our proposed EmoChat over the state-of-the-art methods. Qinfu Xu, Liyuan Pan, Shaozu Yuan, Chunlei Wu	ACM Multimedia	5
2025	Recursive bidirectional cross-modal reasoning network for vision-and-language navigation Jie Wu 0033, Chunlei Wu, Xiuxuan Shen, Fengjiang Wu, Leiquan Wang	Expert Syst. Appl.	2
2025	National COVID Cohort Collaborative data enhancements: a path for expanding common data models abstract OBJECTIVE: To support long COVID research in National COVID Cohort Collaborative (N3C), the N3C Phenotype and Data Acquisition team created data designs to aid contributing sites in enhancing their data. Enhancements include long COVID specialty clinic indicator; Admission, Discharge, and Transfer transactions; patient-level social determinants of health; and in-hospital use of oxygen supplementation. MATERIALS AND METHODS: For each enhancement, we defined the scope and wrote guidance on how to prepare and populate the data in a standardized way. RESULTS: As of June 2024, 29 sites have added at least one data enhancement to their N3C pipeline. DISCUSSION: The use of common data models is critical to the success of N3C; however, these data models cannot account for all needs. Project-driven data enhancement is required. This should be done in a standardized way in alignment with common data model specifications. Our approach offers a useful pathway for enhancing data to improve fit for purpose. CONCLUSION: In this initiative, we rapidly produced project-specific data modeling guidance and documentation in support of long COVID research while maintaining a commitment to terminology standards and harmonized data. Kellie M. Walters, Marshall Clark, Sofia Dard, Stephanie S. Hong, Elizabeth Kelly, Kristin Kostka, Adam M. Lee, Robert T. Miller, Michele Morris, Matvey Palchuk, Emily R. Pfaff, Adam B. Wilcox, Alexis Graves, Alfred Anzalone, Amin Manna, Amit Saha, Amy Olex, Andrea Zhou, Andrew E. Williams, Andrew Southerland, Andrew T. Girvin, Anita Walden, Anjali A Sharathkumar, Benjamin R. C. Amor, Benjamin Bates, Brian Hendricks, Caleb Alexander, Carolyn T. Bramante, Cavin Ward-Caviness, Charisse R. Madlock-Brown, Christine Suver, Christopher G. Chute, Christopher Dillon, Chunlei Wu, Clare Schmitt, Cliff Takemoto, Dan Housman, Davera Gabriel, David Eichmann, Diego Mazzotti, Don Brown, Eilis A. Boudreau, Elaine L. Hill, Elizabeth Zampino, Emily Carlson Marti, Evan French, Farrukh M. Koraishy, Federico Mariona, Fred W. Prior, George Sokos, Greg Martin, Harold P. Lehmann, Heidi Spratt, Hemalkumar Mehta, Hythem Sidky, J. W. Awori Hayanga, Jami Pincavitch, Jaylyn Clark, Jeremy Richard Harper, Jessica Islam, Jin Ge, Joel Gagnier, Joel H. Saltz, Johanna Loomba, John Buse, Jomol P. Mathew, Joni L. Rutter, Julie A. McMurry, Justin Guinney, Justin Starren, Karen Crowley, Katie Rebecca Bradwell, Ken Wilkins, Kenneth R. Gersing, Kenrick Dwain Cato, Kimberly Murray, Lavance Northington, Lee Allan Pyles, Leonie Misquitta, Lesley Cottrell, Lili M. Portilla, Mariam Deacy, Mark M. Bissell, Mary Emmett, Mary Morrison Saltz, Melissa A. Haendel, Meredith C. B. Adams, Meredith Temple-O'Connor, Michael G. Kurilla, Nabeel Qureshi, Nasia Safdar, Nicole Garbarini, Noha Sharafeldin, Ofer Sadan, Patricia A. Francis, Penny Wung Burgoon, Peter N. Robinson, Philip R. O. Payne, Rafael Fuentes, Randeep Jawa, Rebecca Erwin-Cohen, Rena Patel, Richard A. Moffitt, Richard L. Zhu, Rishi Kamaleswaran, Robert Hurley, Saiju Pyarajan, Samuel G. Michael, Samuel Bozzette, Sandeep Mallipattu, Satyanarayana Vedula, Scott Chapman, Shawn T. O'Neil, Soko Setoguchi, Tellen D. Bennett, Tiffany Callahan, Umit Topaloglu, Usman Sheikh, Valery Gordon, Vignesh Subbian, Warren A. Kibbe, Wenndy Hernandez, Will Beasley, Will Cooper, William Hillegass, Xiaohan Tanner Zhang	J. Am. Medical Informatics Assoc.	35
2025	Adaptive Cross-Modal Experts Network with Uncertainty-Driven Fusion for Vision-Language Navigation Jie Wu 0033, Chunlei Wu, Xiuxuan Shen, Leiquan Wang	Knowl. Based Syst.	2
2025	Learning contrastive semantic decomposition for visual grounding Jie Wu 0033, Chunlei Wu, Qinfu Xu, Faming Gong	Neural Networks	2
2024	Memory Self-Calibrated Network for Visual Grounding abstract Visual Grounding (VG) aims to locate the most relevant object or region in an image according to a natural language query. Existing methods in VG utilize fixed image and text representations to capture cross-modal semantic consistency, which limits the flexibility in adjusting image representations according to diverse textual information and hinders performance. To handle this limitation, we propose a novel Memory Self-Calibrated Network (MSCN) by dynamically refining image representations based on the query, thereby improving the semantic consistency between texts and images for visual grounding. Specifically, we introduce two modules: Semantic Relevance Filtering Module (SRFM) and Adaptive Memory Fusion Module (AMFM), to explicitly model the relationship between image and text. SRFM focuses on filtering out image information that is irrelevant to the query, while AMFM adaptively fuses text-related representations with initial image features to enhance the understanding ability of the MSCN model. Comprehensive experiments on three datasets demonstrate the superiority of our method compared to existing approaches. Jie Wu 0033, Chunlei Wu, Xiuxuan Shen, Leiquan Wang	ICASSP	2
2024	Multi-receptive Field Distillation Network for seismic velocity model building Jing Lu 0013, Chunlei Wu, Guolong Li, Shaozu Yuan	Eng. Appl. Artif. Intell.	2
2024	Improving visual grounding with multi-scale discrepancy information and centralized-transformer Jie Wu 0033, Chunlei Wu, Fuyan Wang, Leiquan Wang	Expert Syst. Appl.	2
2024	Vertical-horizontal latent space with iterative memory review network for multi-class anomaly detection Chunlei Wu, Jie Wu 0033, Huan Zhang 0015, Leiquan Wang	Knowl. Based Syst.	1
2024	Towards visual emotion analysis via Multi-Perspective Prompt Learning with Residual-Enhanced Adapter Chunlei Wu, Qinfu Xu, Shaozu Yuan, Jie Wu 0033, Leiquan Wang	Knowl. Based Syst.	1
2024	Multistage Synergistic Aggregation Network for Remote Sensing Visual Grounding abstract Visual Grounding has a broad application prospect in the field of remote sensing. Current state-of-the-art methods predominantly are based on the transformer architecture, utilizing multi-head self-attention in multi-modal encoders to integrate visual and textual features. However, they typically rely on a single fusion approach, which may limit the model’s capacity to learn intricate correlations between textual semantics and visual information. Moreover, they did not establish a direct dependency between features and bounding box representations, thereby restricting the fusion features to conventional object detection paradigm. Consequently, the interactions between regression results and encoded features are constrained. To address these limitations, a generative paradigm is harnessed to directly generate discrete coordinates sequence in an auto-regressive manner, which explores the interaction between direct regression features and encoded multi-modal features. Meanwhile, a novel multi-stage synergistic aggregation module is proposed to facilitate the acquisition of multi-modal features at multiple scales by effectively aggregating visual and textual contexts, enhancing the overall performance. In this work, we validate our framework on the DIOR-RSVG dataset and conduct a comparative analysis with existing methods, achieving a noteworthy improvement in accuracy. The proposed approach presents a promising direction for advancing visual grounding techniques in the context of remote sensing applications. The related code and weights are available at https://github.com/waynamigo/MSAM. Fuyan Wang, Chunlei Wu, Jie Wu 0033, Leiquan Wang, Canwei Li	IEEE Geosci. Remote. Sens. Lett.	2
2024	Summator-Subtractor Network: Modeling Spatial and Channel Differences for Change Detection abstract The field of remote sensing (RS) image change detection (CD) has made significant progress, largely due to the powerful feature representation abilities of deep learning. However, traditional methods have not fully exploited the valuable information in differences. These methods often treat deep models as tools to extract features from individual images, which limits their ability to effectively describe differences. Additionally, many approaches tend to focus on spatial differences, while neglecting variations in the channel dimension. In this study, we introduce a novel Summator–Subtractor network for CD (${S}^{2}$CD), which adeptly captures subtle differences within both the spatial and channel aspects of bi-temporal images. The initial spatial and channel differences are derived through summation and subtraction operations on the bi-temporal images. The summator computes initial channel variations, while the subtractor captures initial spatial disparities. Transformers are then used to pull out meaningful differences in both spatial and channel patterns, allowing for a more nuanced understanding than methods relying solely on features from individual images. Finally, a heterogeneous modulation block integrates channel and spatial difference features, thus amplifying overall differences. Through extensive experimentation on four widely acknowledged CD benchmark datasets, our proposed${S}^{2}$CD method outperforms existing techniques, showcasing its superior performance and promising potential. The codes of this work will be available for the sake of reproducibility at:https://github.com/qianday/SSCD-CD. Leiquan Wang, Ye Fang, Chunlei Wu, Mingming Xu 0001, Ming-Wen Shao	IEEE Trans. Geosci. Remote. Sens.	4
2024	TDWCNet: Triple UNet With Dual-Window Convolution for Hyperspectral Anomaly Detection abstract In recent years, deep learning technology has emerged as the primary research focus in the field of hyperspectral anomaly detection (HAD) and has demonstrated satisfactory detection performance. Existing deep learning-based methods mainly utilize reconstruction errors as criteria for anomaly detection. However, they lack effective suppression of anomaly information in the background reconstruction process, and encounter challenges in addressing scenarios involving the coexistence of multiscale anomalies, which limits the performance of HAD. In order to reconstruct clean and reliable background images, this article proposes a Triple-UNet with dual-window convolution called TDWCNet for HAD. Specifically, we introduce a dual-window convolution that shields pixels within the inner window and only utilizes pixels between the inner and outer windows to reconstruct the central pixel. Based on the dual-window convolution, we construct the DWCBlock module, which serves as the core component for background reconstruction. To address the coexistence of multiscale anomalies, the Triple-UNet structure is designed, which organically combines three DWCBlock modules to gradually eliminate abnormal pixels that are inadvertently reconstructed due to inappropriate convolution kernels. Furthermore, adaptive mean-squared error (mse) and structural similarity index (SSIM) losses are employed to suppress anomaly reconstruction. Extensive experiments conducted on four publicly available datasets demonstrate that TDWCNet achieves satisfactory detection performance. The codes of this work will be available for the sake of reproducibility at:https://github.com/szc2277/TDWCNet-HAD. Leiquan Wang, Zhicheng Sun 0005, Chunlei Wu, Mingming Xu 0001	IEEE Trans. Geosci. Remote. Sens.	4
2024	SRNSD: Structure-Regularized Night-Time Self-Supervised Monocular Depth Estimation for Outdoor Scenes abstract Deep CNNs have achieved impressive improvements for night-time self-supervised depth estimation form a monocular image. However, the performance degrades considerably compared to day-time depth estimation due to significant domain gaps, low visibility, and varying illuminations between day and night images. To address these challenges, we propose a novel night-time self-supervised monocular depth estimation framework with structure regularization, i.e., SRNSD, which incorporates three aspects of constraints for better performance, including feature and depth domain adaptation, image perspective constraint, and cropped multi-scale consistency loss. Specifically, we utilize adaptations of both feature and depth output spaces for better night-time feature extraction and depth map prediction, along with high- and low-frequency decoupling operations for better depth structure and texture recovery. Meanwhile, we employ an image perspective constraint to enhance the smoothness and obtain better depth maps in areas where the luminosity jumps change. Furthermore, we introduce a simple yet effective cropped multi-scale consistency loss that utilizes consistency among different scales of depth outputs for further optimization, refining the detailed textures and structures of predicted depth. Experimental results on different benchmarks with depth ranges of 40m and 60m, including Oxford RobotCar dataset, nuScenes dataset and CARLA-EPE dataset, demonstrate the superiority of our approach over state-of-the-art night-time self-supervised depth estimation approaches across multiple metrics, proving our effectiveness. Runmin Cong, Chunlei Wu, Xibin Song, Wei Zhang 0021, Sam Kwong, Hongdong Li, Pan Ji	IEEE Trans. Image Process.	2
2023	Nested Attention Network with Graph Filtering for Visual Question and Answering abstract Recently, Visual Question Answering(VQA), which is required to generate the answer by understanding both visual and textual content, has attracted considerable research interest. Most existing works extract visual features with the CNN network and learn its feature embedding with an attention mechanism. However, this mechanism may ignore the interaction between entities in the image, which has a fuzzy impact on the answer generation. To better explore the relationship between different entities in the image, a novel Nested Attention Network with Graph Filtering (NANGF) is proposed. It composes of two novel designed modules: a graph filtering mechanism to mine more precise visual semantics and avoid understanding deviation and nested attention to effectively guide the integration of visual features and question features. Extensive experiments conducted on the VQA2.0 datasets demonstrate the effectiveness of the proposed method. Jing Lu 0013, Chunlei Wu, Leiquan Wang, Shaozu Yuan, Jie Wu 0033	ICASSP	2
2023	BioThings Explorer: a query engine for a federated knowledge graph of biomedical APIs abstract Knowledge graphs are an increasingly common data structure for representing biomedical information. These knowledge graphs can easily represent heterogeneous types of information, and many algorithms and tools exist for querying and analyzing graphs. Biomedical knowledge graphs have been used in a variety of applications, including drug repurposing, identification of drug targets, prediction of drug side effects, and clinical decision support. Typically, knowledge graphs are constructed by centralization and integration of data from multiple disparate sources. Here, we describe BioThings Explorer, an application that can query a virtual, federated knowledge graph derived from the aggregated information in a network of biomedical web services. BioThings Explorer leverages semantically precise annotations of the inputs and outputs for each resource, and automates the chaining of web service calls to execute multi-step graph queries. Because there is no large, centralized knowledge graph to maintain, BioThing Explorer is distributed as a lightweight application that dynamically retrieves information at query time. More information can be found at https://explorer.biothings.io, and code is available at https://github.com/biothings/biothings_explorer. Jackson Callaghan, Colleen H. Xu, Jiwen Xin, Marco Alvarado Cano, Anders Riutta, Eric Zhou, Rohan Juneja, Yao Yao 0007, Madhumita Narayan, Kristina Hanspers, Ayushi Agrawal, Alexander R. Pico, Chunlei Wu, Andrew I. Su	Bioinform.	13
2023	Schema Playground: a tool for authoring, extending, and using metadata schemas to improve FAIRness of biomedical data abstract BACKGROUND: Biomedical researchers are strongly encouraged to make their research outputs more Findable, Accessible, Interoperable, and Reusable (FAIR). While many biomedical research outputs are more readily accessible through open data efforts, finding relevant outputs remains a significant challenge. Schema.org is a metadata vocabulary standardization project that enables web content creators to make their content more FAIR. Leveraging Schema.org could benefit biomedical research resource providers, but it can be challenging to apply Schema.org standards to biomedical research outputs. We created an online browser-based tool that empowers researchers and repository developers to utilize Schema.org or other biomedical schema projects. RESULTS: Our browser-based tool includes features which can help address many of the barriers towards Schema.org-compliance such as: The ability to easily browse for relevant Schema.org classes, the ability to extend and customize a class to be more suitable for biomedical research outputs, the ability to create data validation to ensure adherence of a research output to a customized class, and the ability to register a custom class to our schema registry enabling others to search and re-use it. We demonstrate the use of our tool with the creation of the Outbreak.info schema-a large multi-class schema for harmonizing various COVID-19 related resources. CONCLUSIONS: We have created a browser-based tool to empower biomedical research resource providers to leverage Schema.org classes to make their research outputs more FAIR. Marco Alvarado Cano, Ginger Tsueng, Xinghua Zhou, Jiwen Xin, Laura D. Hughes, Julia Mullen, Andrew I. Su, Chunlei Wu	BMC Bioinform.	8
2023	Multi-view inter-modality representation with progressive fusion for image-text matching Jie Wu 0033, Leiquan Wang, Chenglizhao Chen, Jing Lu 0013, Chunlei Wu	Neurocomputing	5
2023	A multimodal dialogue system for improving user satisfaction via knowledge-enriched response and image recommendation Jiangnan Wang, Hai-Sheng Li 0002, Leiquan Wang, Chunlei Wu	Neural Comput. Appl.	4
2023	Adversarial MixUp with implicit semantic preservation for semi-supervised hyperspectral image classification Leiquan Wang, Jialiang Zhou, Chunlei Wu, Mingming Xu 0001	Signal Process.	5
2023	Dynamic Pruning of Regions for Image-Sentence Matching abstract Image–sentence matching is becoming increasingly essential in the integrated understanding of vision and language. Prior approaches apply a pre-trained detection model to extract region features and explore fine-grained relationships between image and sentence by aggregating the similarities of all region–word pairs. However, all images are represented by the same number of regions, regardless of their respective semantic complexity, which results in a large number of redundant regions interfering with semantic inference and bringing additional computational burden. To address the lack of flexibility in image representation and information redundancy, a novel method named Dynamic Pruning of Regions for Image–Sentence Matching (DPRM) is proposed to efficiently capture relationships between text and image. In particular, a dynamic region pruning module is presented to dynamically select the appropriate number of regions according to the semantic complexity of each image, thus pruning redundant regions and reducing superfluous computations. Moreover, an inter-modality refinement module is designed to refine the fine-grained relationships of region–word pairs by retaining meaningful interaction features and suppressing interference from redundant alignments, which learns the more accurate semantic correspondences. Extensive experiments on MSCOCO and Flickr30K datasets prove the superiority of DPRM compared with previous approaches. Jie Wu 0033, Weifeng Liu 0001, Leiquan Wang, Xiuxuan Shen, Chunlei Wu	Signal Process. Image Commun.	6
2023	Multiscale Fusion Network With SR-Attention for Seismic Velocity Model Building abstract Seismic velocity is crucial for seismic waveform inversion in geological exploration. An accurate velocity model is a key prerequisite for reverse time migration and other high-resolution seismic imaging techniques. Traditional methods perform well in seismic wave velocity modeling, but there are issues such as lack of low-frequency components, low computational efficiency, and subjective factors, which result in low accuracy in modeling seismic wave velocity containing noise. In addition, mid-to-low frequency data is crucial for velocity model inversion, but existing methods often overlook this. In this paper, we present a Multi-scale Fusion Network with Shot-Record attention module (MFNSR), which can construct velocity models directly from the original seismic record. The proposed network can obtain finer-grained complete semantic information in the shot record by multi-layer fusion operation. SR-attention is proposed to reveal the medium-low frequency information in the shot record. The proposed Random Noise Block enables better generalization of the model and higher accuracy in modeling the shot record speed of the entrained noise. The results of extensive numerical experiments on synthetic models show that our method acquires outstanding performance, which verifies the positive effect of MFNSR on the inversion of medium-low frequency data. The visualizations of outputs show that the proposed method can obtain more accurate velocity models. Jing Lu 0013, Chunlei Wu, Yingming Qu, Huan Zhang 0015	IEEE Trans. Geosci. Remote. Sens.	2
2023	Eliminating Spatial Correlations of Anomaly: Corner-Visible Network for Unsupervised Hyperspectral Anomaly Detection abstract Hyperspectral anomaly detection (HAD) is crucial for identifying and analyzing abnormal objects in various domains. While existing methods have shown promising results by designing detection methods tailored to specific anomaly characteristics, there is a need for a highly versatile approach that can effectively handle anomalies, particularly those with large spatial sizes. In this article, we propose an end-to-end corner-visible network (CVNet) for unsupervised HAD. Specifically, we introduce a corner-visible convolution that leverages the statistical dependencies of the background within the receptive field while eliminating spatial correlations with potential anomalies for background generation. To address the grid effect caused by the corner-visible convolution, a background smoothing module is employed by using the conventional convolution. Furthermore, adaptive mean-squared error (MSE) and structural similarity index (SSIM) losses are employed to suppress anomaly reconstruction, resulting in a reliable reconstructed background map. Anomalies are identified through the residual of the original hyperspectral image (HSI) and the reconstructed background. Extensive experiments conducted on three publicly datasets demonstrate the effectiveness of our proposed method in handling different types of anomalies. The state-of-the-art performance showcases the versatility and applicability of CVNet in HAD. The codes of this work will be available for the sake of reproducibility athttps://github.com/Cloudynewbee/CVNet-HAD. Leiquan Wang, Chunlei Wu, Mingming Xu 0001, Ming-Wen Shao	IEEE Trans. Geosci. Remote. Sens.	4
2023	Attentive-Adaptive Network for Hyperspectral Images Classification With Noisy Labels abstract With the development of deep neural networks, hyperpsectral image (HSI) classification systems have achieved a significant improvement. These systems require numerous and accurate labeled hyperspectral data to be adequately trained. However, noisy labels are inherent in real-world hyperspectral systems, resulting in unreliable decisions. To handle noisy labels in hyperpsectral classification, an end-to-end attentive-adaptive network (AAN) is proposed for robust HSI classification training. The goal is to build a classifier with strong generalization capabilities that can be applied to both clean and noisy training sets without explicit noise label pre-treatment. Specifically, a spectral stem network with non-adjacent shortcut is exploited initially to re-distribute the sensitive layers for noisy labels to achieve robust spectral representation. Then, a group-shuffle attention module is proposed to capture the discriminative and robust spatial-spectral features in the presence of noisy labels. Finally, an adaptive noise-robust loss function is developed to fight against noisy labels by learning a parameter to balance the normalized cross entropy (NCE) and reverse cross entropy (RCE). Experimental results on three HSI benchmark datasets with simulated noisy labels demonstrate the effectiveness of AAN on HSI classification. Leiquan Wang, Tongchuan Zhu, Neeraj Kumar 0001, Chunlei Wu, Peiying Zhang 0001	IEEE Trans. Geosci. Remote. Sens.	5
2022	BioThings SDK: a toolkit for building high-performance data APIs in biomedical research abstract SUMMARY: To meet the increased need of making biomedical resources more accessible and reusable, Web Application Programming Interfaces (APIs) or web services have become a common way to disseminate knowledge sources. The BioThings APIs are a collection of high-performance, scalable, annotation as a service APIs that automate the integration of biological annotations from disparate data sources. This collection of APIs currently includes MyGene.info, MyVariant.info and MyChem.info for integrating annotations on genes, variants and chemical compounds, respectively. These APIs are used by both individual researchers and application developers to simplify the process of annotation retrieval and identifier mapping. Here, we describe the BioThings Software Development Kit (SDK), a generalizable and reusable toolkit for integrating data from multiple disparate data sources and creating high-performance APIs. This toolkit allows users to easily create their own BioThings APIs for any data type of interest to them, as well as keep APIs up-to-date with their underlying data sources. AVAILABILITY AND IMPLEMENTATION: The BioThings SDK is built in Python and released via PyPI (https://pypi.org/project/biothings/). Its source code is hosted at its github repository (https://github.com/biothings/biothings.api). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. Sebastien Lelong, Xinghua Zhou, Cyrus Afrasiabi, Zhongchao Qian, Marco Alvarado Cano, Ginger Tsueng, Jiwen Xin, Julia Mullen, Yao Yao 0007, Ricardo Avila, Greg Taylor, Andrew I. Su, Chunlei Wu	Bioinform.	13
2022	Anti-jamming heart rate estimation using a spatial-temporal fusion network Chunlei Wu, Ziyu Yuan, Shaohua Wan 0001, Leiquan Wang, Weishan Zhang	Comput. Vis. Image Underst.	1
2022	Sequential Transformer via an Outside-In Attention for image captioning Chunlei Wu, Guohe Li	Eng. Appl. Artif. Intell.	2
2022	Generating diverse chinese poetry from images via unsupervised method Jiangnan Wang, Hai-Sheng Li 0002, Chunlei Wu, Faming Gong, Leiquan Wang	Neurocomputing	3
2022	Demonstrating an approach for evaluating synthetic geospatial and temporal epidemiologic data utility: results from analyzing >1.8 million SARS-CoV-2 tests in the United States National COVID Cohort Collaborative (N3C) abstract OBJECTIVE: This study sought to evaluate whether synthetic data derived from a national coronavirus disease 2019 (COVID-19) dataset could be used for geospatial and temporal epidemic analyses. MATERIALS AND METHODS: Using an original dataset (n = 1 854 968 severe acute respiratory syndrome coronavirus 2 tests) and its synthetic derivative, we compared key indicators of COVID-19 community spread through analysis of aggregate and zip code-level epidemic curves, patient characteristics and outcomes, distribution of tests by zip code, and indicator counts stratified by month and zip code. Similarity between the data was statistically and qualitatively evaluated. RESULTS: In general, synthetic data closely matched original data for epidemic curves, patient characteristics, and outcomes. Synthetic data suppressed labels of zip codes with few total tests (mean = 2.9 ± 2.4; max = 16 tests; 66% reduction of unique zip codes). Epidemic curves and monthly indicator counts were similar between synthetic and original data in a random sample of the most tested (top 1%; n = 171) and for all unsuppressed zip codes (n = 5819), respectively. In small sample sizes, synthetic data utility was notably decreased. DISCUSSION: Analyses on the population-level and of densely tested zip codes (which contained most of the data) were similar between original and synthetically derived datasets. Analyses of sparsely tested populations were less similar and had more data suppression. CONCLUSION: In general, synthetic data were successfully used to analyze geospatial and temporal trends. Analyses using small sample sizes or populations were limited, in part due to purposeful data label suppression-an attribute disclosure countermeasure. Users should consider data fitness for use in these cases. Jason A. Thomas, Randi E. Foraker, Noa Zamstein, Jon D. Morrow, Philip R. O. Payne, Adam B. Wilcox, Melissa A. Haendel, Christopher G. Chute, Kenneth R. Gersing, Anita Walden, Tellen D. Bennett, David Eichmann, Justin Guinney, Warren A. Kibbe, Emily R. Pfaff, Peter N. Robinson, Joel H. Saltz, Heidi Spratt, Justin Starren, Christine Suver, Chunlei Wu, Davera Gabriel, Stephanie S. Hong, Kristin Kostka, Harold P. Lehmann, Richard A. Moffitt, Michele Morris, Matvey Palchuk, Xiaohan Tanner Zhang, Richard L. Zhu, Benjamin R. C. Amor, Mark M. Bissell, Marshall Clark, Andrew T. Girvin, Adam M. Lee, Robert T. Miller, Kellie M. Walters, Yooree Chae, Connor Cook, Alexandra Dest, Racquel R. Dietz, Thomas Dillon, Patricia A. Francis, Rafael Fuentes, Alexis Graves, Andrew J. Neumann, Shawn T. O'Neil, Usman Sheikh, Andréa M. Volz, Elizabeth Zampino, Christopher P. Austin, Samuel Bozzette, Mariam Deacy, Nicole Garbarini, Michael G. Kurilla, Samuel G. Michael, Joni L. Rutter, Meredith Temple-O'Connor, Katie Rebecca Bradwell, Amin Manna, Nabeel Qureshi, Mary Morrison Saltz, Julie A. McMurry, Carolyn T. Bramante, Jeremy Richard Harper, Wenndy Hernandez, Farrukh M. Koraishy, Federico Mariona, Saidulu Mattapally, Amit Saha, Satyanarayana Vedula, Yujuan Fu, Nisha Mathews, Ofer Mendelevitch	J. Am. Medical Informatics Assoc.	22
2022	Region Reinforcement Network With Topic Constraint for Image-Text Matching abstract Image and sentence matching has attracted increasing attention since it is associated with two important modalities of vision and language. Previous methods aim to find the latent correspondences between image regions and words by aggregating the similarities of the region-word pairs. However, these approaches consider little about the relationships of diverse regions in the image and treat the similarities of all region-word pairs equally. Moreover, focusing on fine-grained alignment overly, the true meaning of the original image will be likely distorted. In this paper, a novel Region Reinforcement Network with Topic Constraint (RRTC) is proposed to explore the correspondences between images and texts. Specifically, the region reinforcement network is built to infer fine-grained correspondence by considering the relationships of regions and re-assigning region-word similarities. Meanwhile, the topic constraint module is presented to summarize the central theme of images, which constrains the original image deviation. Extensive experimental results on MSCOCO and Flickr30k datasets verify the effectiveness of our proposed RRTC. Jie Wu 0033, Chunlei Wu, Jing Lu 0013, Leiquan Wang, Xue-rong Cui	IEEE Trans. Circuits Syst. Video Technol.	2
2022	Multiscale Contrastive Learning Networks for Automatic Denoising of Geological Sedimentary Model Images abstract The well-described river courses in geological sedimentary models are essential for identifying oil and gas reservoirs. However, numerous noises are generated around the river course, including irregular noises and regions due to errors in the geological data, as well as traces left over from the printed model. The cluttered distributions of noises make the complete river course unobtainable, which interferes with reservoir prediction. To the best of our knowledge, deep learning-based methods for automatic noise detection and removal have not been explored in the field of processing geological sedimentary model images. In this paper, we present Multi-scale Contrastive Learning Networks (CLGAN) for detecting noise in geological sedimentary model images. A multi-scale contrastive training strategy is proposed to capture noise locations and river discontinuities by comparing the distributions with and without noise in image space and feature space. A paired dataset that consists of images with noise and images without noise is constructed for contrastive training. Moreover, cyclic denoising is proposed to completely denoise by constantly modifying the pixel values at the noise, which prevents missed detections by calling the model multiple times. Subsequently, pixel-level denoising is designed to initially remove a portion of the noise by contouring non-river regions, which reduces the pressure on the cyclic denoising method. The detection results demonstrate the effectiveness of CLGAN. The denoising results with excellent river connectivity and integrity highlight the superiority of the proposed denoising methods. Chunlei Wu, Huan Zhang 0015, Leiquan Wang	IEEE Trans. Geosci. Remote. Sens.	1
2021	Dual-View Semantic Inference Network for image-text matching Chunlei Wu, Jie Wu 0033, Haiwen Cao, Leiquan Wang	Neurocomputing	1
2021	The National COVID Cohort Collaborative (N3C): Rationale, design, infrastructure, and deployment abstract OBJECTIVE: Coronavirus disease 2019 (COVID-19) poses societal challenges that require expeditious data and knowledge sharing. Though organizational clinical data are abundant, these are largely inaccessible to outside researchers. Statistical, machine learning, and causal analyses are most successful with large-scale data beyond what is available in any given organization. Here, we introduce the National COVID Cohort Collaborative (N3C), an open science community focused on analyzing patient-level data from many centers. MATERIALS AND METHODS: The Clinical and Translational Science Award Program and scientific community created N3C to overcome technical, regulatory, policy, and governance barriers to sharing and harmonizing individual-level clinical data. We developed solutions to extract, aggregate, and harmonize data across organizations and data models, and created a secure data enclave to enable efficient, transparent, and reproducible collaborative analytics. RESULTS: Organized in inclusive workstreams, we created legal agreements and governance for organizations and researchers; data extraction scripts to identify and ingest positive, negative, and possible COVID-19 cases; a data quality assurance and harmonization pipeline to create a single harmonized dataset; population of the secure data enclave with data, machine learning, and statistical analytics tools; dissemination mechanisms; and a synthetic data pilot to democratize data access. CONCLUSIONS: The N3C has demonstrated that a multisite collaborative learning health network can overcome barriers to rapidly build a scalable infrastructure incorporating multiorganizational clinical data for COVID-19 analytics. We expect this effort to save lives by enabling rapid collaboration among clinicians, researchers, and data scientists to identify treatments and specialized care and thereby reduce the immediate and long-term impacts of COVID-19. Melissa A. Haendel, Christopher G. Chute, Tellen D. Bennett, David Eichmann, Justin Guinney, Warren A. Kibbe, Philip R. O. Payne, Emily R. Pfaff, Peter N. Robinson, Joel H. Saltz, Heidi Spratt, Christine Suver, John Wilbanks, Adam B. Wilcox, Andrew E. Williams, Chunlei Wu, Clair Blacketer, Robert L. Bradford, James J. Cimino, Marshall Clark, Evan W. Colmenares, Patricia A. Francis, Davera Gabriel, Alexis Graves, Raju Hemadri, Stephanie S. Hong, George Hripcsak, Dazhi Jiao, Jeffrey G. Klann, Kristin Kostka, Adam M. Lee, Harold P. Lehmann, Lora Lingrey, Robert T. Miller, Michele Morris, Shawn N. Murphy, Karthik Natarajan, Matvey Palchuk, Usman Sheikh, Harold R. Solbrig, Shyam Visweswaran, Anita Walden, Kellie M. Walters, Griffin M. Weber, Xiaohan Tanner Zhang, Richard L. Zhu, Benjamin R. C. Amor, Andrew T. Girvin, Amin Manna, Nabeel Qureshi, Michael G. Kurilla, Samuel G. Michael, Lili M. Portilla, Joni L. Rutter, Christopher P. Austin, Kenneth R. Gersing	J. Am. Medical Informatics Assoc.	16
2021	Generate classical Chinese poems with theme-style from images Chunlei Wu, Jiangnan Wang, Shaozu Yuan, Leiquan Wang, Weishan Zhang	Pattern Recognit. Lett.	1
2021	Past is important: Improved image captioning by looking back in time Chunlei Wu, Zhiyang Jia, Xufei Hu	Signal Process. Image Commun.	2
2020	Multi-Attention Generative Adversarial Network for image captioning Leiquan Wang, Haiwen Cao, Ming-Wen Shao, Chunlei Wu	Neurocomputing	5
2018	Cross-linking BioThings APIs through JSON-LD to facilitate knowledge exploration abstract BACKGROUND: Application Programming Interfaces (APIs) are now widely used to distribute biological data. And many popular biological APIs developed by many different research teams have adopted Javascript Object Notation (JSON) as their primary data format. While usage of a common data format offers significant advantages, that alone is not sufficient for rich integrative queries across APIs. RESULTS: Here, we have implemented JSON for Linking Data (JSON-LD) technology on the BioThings APIs that we have developed, MyGene.info , MyVariant.info and MyChem.info . JSON-LD provides a standard way to add semantic context to the existing JSON data structure, for the purpose of enhancing the interoperability between APIs. We demonstrated several use cases that were facilitated by semantic annotations using JSON-LD, including simpler and more precise query capabilities as well as API cross-linking. CONCLUSIONS: We believe that this pattern offers a generalizable solution for interoperability of APIs in the life sciences. Jiwen Xin, Cyrus Afrasiabi, Sebastien Lelong, Julee Adesara, Ginger Tsueng, Andrew I. Su, Chunlei Wu	BMC Bioinform.	7
2018	Hierarchical attention-based multimodal fusion for video captioning Chunlei Wu, Xiaoliang Chu, Weichen Sun, Leiquan Wang	Neurocomputing	1
2018	Modeling visual and word-conditional semantic attention for image captioning Chunlei Wu, Xiaoliang Chu, Leiquan Wang	Signal Process. Image Commun.	1
2017	smartAPI: Towards a More Intelligent Network of Web APIs Amrapali Zaveri, Shima Dastgheib, Chunlei Wu, Trish Whetzel, Ruben Verborgh, Paul Avillach, Gabor Korodi, Raymond Terryn, Kathleen M. Jagodnik, Pedro Assis, Michel Dumontier	ESWC (2)	3
2015	Analytical current model of tunneling field-effect transistor considering the impacts of both gate and drain voltages on tunneling Chunlei Wu, Ru Huang 0001	Sci. China Inf. Sci.	2
2011	TCLUST: A Fast Method for Clustering Genome-Scale Expression Data abstract Genes with a common function are often hypothesized to have correlated expression levels in mRNA expression data, motivating the development of clustering algorithms for gene expression data sets. We observe that existing approaches do not scale well for large data sets, and indeed did not converge for the data set considered here. We present a novel clustering method TCLUST that exploits coconnectedness to efficiently cluster large, sparse expression data. We compare our approach with two existing clustering methods CAST and K-means which have been previously applied to clustering of gene-expression data with good performance results. Using a number of metrics, TCLUST is shown to be superior to or at least competitive with the other methods, while being much faster. We have applied this clustering algorithm to a genome-scale gene-expression data set and used gene set enrichment analysis to discover highly significant biological clusters. (Source code for TCLUST is downloadable at http://www.cse.ucsd.edu/~bdost/tclust.) Banu Dost, Chunlei Wu, Andrew I. Su, Vineet Bafna	IEEE ACM Trans. Comput. Biol. Bioinform.	2
2007	Short oligonucleotide probes containing G-stacks display abnormal binding affinity on Affymetrix microarrays abstract MOTIVATION: In microarray experiments, probe design is critical to the specific and accurate measurement of target concentrations. Current designs select suitable probes through in silico scanning of transcriptome/genome based on first principles. However, due to lack of tools, the observed microarray data have not been used to assess the performance of individual probes to provide feedback to improve future designs. RESULT: In this study, we describe a probe performance assessment method based on the concordance of the observed signals from probes that share common targets. Using this method, we found that probes containing multiple guanines in a row (G-stacks) have abnormal binding behavior compared with other probes, both in gene expression assays and genotyping assays using Affymetrix microarrays. These probes are less likely to covary with other probes that interrogate the same genes. Moreover, we found that these probes are much more likely to produce outliers when fitting the observed signals according to the positional dependent nearest neighbor model, which gives reasonable estimates of binding affinity for most other probes. These results suggest that probes containing G-stacks tend to have increased cross hybridization signals and reduced target-specific hybridization signals, presumably due to multiplex binding forming G-quartet structures. Our findings are expected to be useful in microarray design and data analysis. Chunlei Wu, Keith A. Baggerly, Roberto Carta	Bioinform.	1
2005	Applications of beta-mixture models in bioinformatics abstract SUMMARY: We propose a beta-mixture model approach to solve a variety of problems related to correlations of gene-expression levels. For example, in meta-analyses of microarray gene-expression datasets, a threshold value of correlation coefficients for gene-expression levels is used to decide whether gene-expression levels are strongly correlated across studies. Ad hoc threshold values such as 0.5 are often used. In this paper, we use a beta-mixture model approach to divide the correlation coefficients into several populations so that the large correlation coefficients can be identified. Another important application of the proposed method is in finding co-expressed genes. Two examples are provided to illustrate both applications. Through our analysis, we also discover that the popular model selection criteria BIC and AIC are not suitable for the beta-mixture model. To determine the number of components in the mixture model, we suggest an alternative criterion, ICL-BIC, which is shown to perform better in selecting the correct mixture model. SUPPLEMENTARY INFORMATION: http://odin.mdacc.tmc.edu/~yuanj/highcorgeneanno.html. Chunlei Wu, Jing Wang 0006, Kevin R. Coombes	Bioinform.	2