Huan Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Huan Liu has a total of 73 co-authors. Here are the top co-authors by number of shared publications:
- Dalin Zhang
Hangzhou Dianzi University, Hangzhou, China
11 shared publications - Yuzhe Zhang
School of Computer Science and Technology, Xian Jiaotong University, Xian, China
8 shared publications - Minnan Luo
Xi'an Jiaotong University, Xi'an, China
5 shared publications - Chengxi Xie
School of Computer Science and Technology, Xian Jiaotong University, Xian, China
3 shared publications Guanjian Liu
3 shared publications- Tao Qin
School of Computer Science and Technology, Xian Jiaotong University, Xian, China
3 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (11) , 7750-7763
Synergistic Dual Proxies: Enhancing Cohesion and Separability in Deep Graph Clustering
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (11) , 7750-7763
Synergistic Dual Proxies: Enhancing Cohesion and Separability in Deep Graph Clustering
- 26 June 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 202
HNAS-EEG: Hierarchical neural architecture search for robust multi-source cross-subject EEG emotion recognition
- 26 June 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 202
HNAS-EEG: Hierarchical neural architecture search for robust multi-source cross-subject EEG emotion recognition
- 14 May 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 112, 104125
Rank-aware agglomeration of foundation models for immunohistochemistry image cell counting
- 14 May 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 112, 104125
Rank-aware agglomeration of foundation models for immunohistochemistry image cell counting
- 4 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. PP (23798920) , 1-12
HeteFedEEG: Prototype-Transfer Heterogeneous Federated Learning for EEG-based Emotion Recognition
Electroencephalography (EEG)-based emotion recognition is a promising avenue in affective computing due to its high temporal resolution, non-invasiveness, and cost-effectiveness. However, practical deployment faces significant challenges, including data privacy constraints, environmental noise, and substantial inter-subject variability, which hinder model generalization when trained on isolated datasets. Federated Learning (FL) has emerged as a compelling solution by enabling collaborative training across institutions without sharing raw data. Nevertheless, existing Federated EEG-based Emotion recognition approaches often suffer from two critical forms of heterogeneity: (1) subject heterogeneity, where EEG signals vary significantly across individuals, and (2) model heterogeneity, where clients adopt diverse model architectures and training strategies. To address these challenges, we propose HeteFedEEG, a heterogeneous federated learning framework based on prototype transfer. HeteFedEEG leverages information bottleneck theory to decouple EEG features into emotion-relevant prototypes and individual-specific representations. Instead of sharing model parameters, clients transmit perturbed emotion prototypes, enabling effective cross-institutional collaboration while preserving data privacy. A central server aggregates these prototypes into a unified emotional feature space, facilitating communication across heterogeneous models. Furthermore, to enhance learning stability, we introduce prototype regularization and a lifelong learning loss to mitigate catastrophic forgetting during local updates. Experiments on two public datasets, SEED and DEAP, demonstrate that HeteFedEEG consistently outperforms state-of-the-art methods, achieving an average improvement of 2.7% in accuracy and 1.5% in F1 score. These results highlight the potential of prototype transfer for addressing heterogeneity in federated EEG-based emotion recognition while ensuring privacy and generalizability. The source code is publicly available at https://github.com/XJTU-EEG/HeteFedEEG.
- 4 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. PP (23798920) , 1-12
HeteFedEEG: Prototype-Transfer Heterogeneous Federated Learning for EEG-based Emotion Recognition
Electroencephalography (EEG)-based emotion recognition is a promising avenue in affective computing due to its high temporal resolution, non-invasiveness, and cost-effectiveness. However, practical deployment faces significant challenges, including data privacy constraints, environmental noise, and substantial inter-subject variability, which hinder model generalization when trained on isolated datasets. Federated Learning (FL) has emerged as a compelling solution by enabling collaborative training across institutions without sharing raw data. Nevertheless, existing Federated EEG-based Emotion recognition approaches often suffer from two critical forms of heterogeneity: (1) subject heterogeneity, where EEG signals vary significantly across individuals, and (2) model heterogeneity, where clients adopt diverse model architectures and training strategies. To address these challenges, we propose HeteFedEEG, a heterogeneous federated learning framework based on prototype transfer. HeteFedEEG leverages information bottleneck theory to decouple EEG features into emotion-relevant prototypes and individual-specific representations. Instead of sharing model parameters, clients transmit perturbed emotion prototypes, enabling effective cross-institutional collaboration while preserving data privacy. A central server aggregates these prototypes into a unified emotional feature space, facilitating communication across heterogeneous models. Furthermore, to enhance learning stability, we introduce prototype regularization and a lifelong learning loss to mitigate catastrophic forgetting during local updates. Experiments on two public datasets, SEED and DEAP, demonstrate that HeteFedEEG consistently outperforms state-of-the-art methods, achieving an average improvement of 2.7% in accuracy and 1.5% in F1 score. These results highlight the potential of prototype transfer for addressing heterogeneity in federated EEG-based emotion recognition while ensuring privacy and generalizability. The source code is publicly available at https://github.com/XJTU-EEG/HeteFedEEG.
- Open Access
Rank-Aware Agglomeration of Foundation Models for Immunohistochemistry Image Cell Counting
Accurate cell counting in immunohistochemistry (IHC) images is critical for quantifying protein expression and aiding cancer diagnosis. However, the task remains challenging due to the chromogen overlap, variable biomarker staining, and diverse cellular morphologies. Regression-based counting methods offer advantages over detection-based ones in handling overlapped cells, yet rarely support end-to-end multi-class counting. Moreover, the potential of foundation models remains largely underexplored in this paradigm. To address these limitations, we propose a rank-aware agglomeration framework that selectively distills knowledge from multiple strong foundation models, leveraging their complementary representations to handle IHC heterogeneity and obtain a compact yet effective student model, CountIHC. Unlike prior task-agnostic agglomeration strategies that either treat all teachers equally or rely on feature similarity, we design a Rank-Aware Teacher Selecting (RATS) strategy that models global-to-local patch rankings to assess each teacher's inherent counting capacity and enable sample-wise teacher selection. For multi-class cell counting, we introduce a fine-tuning stage that reformulates the task as vision-language alignment. Discrete semantic anchors derived from structured text prompts encode both category and quantity information, guiding the regression of class-specific density maps and improving counting for overlapping cells. Extensive experiments demonstrate that CountIHC surpasses state-of-the-art methods across 12 IHC biomarkers and 5 tissue types, while exhibiting high agreement with pathologists' assessments. Its effectiveness on H&E-stained data further confirms the scalability of the proposed method.
Open AccessRank-Aware Agglomeration of Foundation Models for Immunohistochemistry Image Cell Counting
Accurate cell counting in immunohistochemistry (IHC) images is critical for quantifying protein expression and aiding cancer diagnosis. However, the task remains challenging due to the chromogen overlap, variable biomarker staining, and diverse cellular morphologies. Regression-based counting methods offer advantages over detection-based ones in handling overlapped cells, yet rarely support end-to-end multi-class counting. Moreover, the potential of foundation models remains largely underexplored in this paradigm. To address these limitations, we propose a rank-aware agglomeration framework that selectively distills knowledge from multiple strong foundation models, leveraging their complementary representations to handle IHC heterogeneity and obtain a compact yet effective student model, CountIHC. Unlike prior task-agnostic agglomeration strategies that either treat all teachers equally or rely on feature similarity, we design a Rank-Aware Teacher Selecting (RATS) strategy that models global-to-local patch rankings to assess each teacher's inherent counting capacity and enable sample-wise teacher selection. For multi-class cell counting, we introduce a fine-tuning stage that reformulates the task as vision-language alignment. Discrete semantic anchors derived from structured text prompts encode both category and quantity information, guiding the regression of class-specific density maps and improving counting for overlapping cells. Extensive experiments demonstrate that CountIHC surpasses state-of-the-art methods across 12 IHC biomarkers and 5 tissue types, while exhibiting high agreement with pathologists' assessments. Its effectiveness on H&E-stained data further confirms the scalability of the proposed method.
- 10 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 17 (1) , 147-161
MIND-EEG: Multi-Granularity Integration Network With Discrete Codebook for EEG-Based Emotion Recognition
Emotion recognition using electroencephalogram (EEG) signals has broad potential across various domains. EEG signals have ability to capture rich spatial information related to brain activity, yet effectively modeling and utilizing these spatial relationships remains a challenge. Existing methods struggle with simplistic spatial structure modeling, failing to capture complex node interactions, and lack generalizable spatial connection representations, failing to balance the dynamic nature of brain networks with the need for discriminative and generalizable features. To address these challenges, we propose the Multi-granularity Integration Network with Discrete Codebook for EEG-based Emotion Recognition (MIND-EEG). The framework employs a multi-granularity approach, integrating global and regional spatial information through a Global State Encoder, an Intra-Regional Functionality Encoder, and an Inter-Regional Interaction Encoder to comprehensively model brain activity. Additionally, we introduce a discrete codebook mechanism for constructing network structures via vector quantization, ensuring compact and meaningful brain network representations while mitigating over-smoothing and enhancing model generalization. The proposed framework effectively captures the dynamic and diverse nature of EEG signals, enabling robust emotion recognition. Extensive comparisons and analyses demonstrate the effectiveness of MIND-EEG, and the source code is publicly available at https://github.com/XJTU-EEG/MIND_EEG.
- 10 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 17 (1) , 147-161
MIND-EEG: Multi-Granularity Integration Network With Discrete Codebook for EEG-Based Emotion Recognition
Emotion recognition using electroencephalogram (EEG) signals has broad potential across various domains. EEG signals have ability to capture rich spatial information related to brain activity, yet effectively modeling and utilizing these spatial relationships remains a challenge. Existing methods struggle with simplistic spatial structure modeling, failing to capture complex node interactions, and lack generalizable spatial connection representations, failing to balance the dynamic nature of brain networks with the need for discriminative and generalizable features. To address these challenges, we propose the Multi-granularity Integration Network with Discrete Codebook for EEG-based Emotion Recognition (MIND-EEG). The framework employs a multi-granularity approach, integrating global and regional spatial information through a Global State Encoder, an Intra-Regional Functionality Encoder, and an Inter-Regional Interaction Encoder to comprehensively model brain activity. Additionally, we introduce a discrete codebook mechanism for constructing network structures via vector quantization, ensuring compact and meaningful brain network representations while mitigating over-smoothing and enhancing model generalization. The proposed framework effectively captures the dynamic and diverse nature of EEG signals, enabling robust emotion recognition. Extensive comparisons and analyses demonstrate the effectiveness of MIND-EEG, and the source code is publicly available at https://github.com/XJTU-EEG/MIND_EEG.
- 4 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 16 (4) , 3596-3613
LibEER: A Comprehensive Benchmark and Algorithm Library for EEG-Based Emotion Recognition
EEG-based emotion recognition (EER) has gained significant attention due to its potential for understanding and analyzing human emotions. While recent advancements in deep learning techniques have substantially improved EER, the field lacks a convincing benchmark and comprehensive open-source libraries. This absence complicates fair comparisons between models and creates reproducibility challenges for practitioners, which collectively hinder progress. To address these issues, we introduce LibEER, a comprehensive benchmark and algorithm library designed to facilitate fair comparisons in EER. LibEER carefully selects popular and powerful baselines, harmonizes key implementation details across methods, and provides a standardized codebase in PyTorch. By offering a consistent evaluation framework with standardized experimental settings, LibEER enables unbiased assessments of seventeen representative deep learning models for EER across the six most widely used datasets. Additionally, we conduct a thorough, reproducible comparison of model performance and efficiency, providing valuable insights to guide researchers in the selection and design of EER models. Moreover, we make observations and in-depth analysis on the experiment results and identify current challenges in this community. We hope that our work will not only lower entry barriers for newcomers to EEG-based emotion recognition but also contribute to the standardization of research in this domain, fostering steady development. The library and source code are publicly available at https://github.com/XJTU-EEG/LibEER.
- 4 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 16 (4) , 3596-3613
LibEER: A Comprehensive Benchmark and Algorithm Library for EEG-Based Emotion Recognition
EEG-based emotion recognition (EER) has gained significant attention due to its potential for understanding and analyzing human emotions. While recent advancements in deep learning techniques have substantially improved EER, the field lacks a convincing benchmark and comprehensive open-source libraries. This absence complicates fair comparisons between models and creates reproducibility challenges for practitioners, which collectively hinder progress. To address these issues, we introduce LibEER, a comprehensive benchmark and algorithm library designed to facilitate fair comparisons in EER. LibEER carefully selects popular and powerful baselines, harmonizes key implementation details across methods, and provides a standardized codebase in PyTorch. By offering a consistent evaluation framework with standardized experimental settings, LibEER enables unbiased assessments of seventeen representative deep learning models for EER across the six most widely used datasets. Additionally, we conduct a thorough, reproducible comparison of model performance and efficiency, providing valuable insights to guide researchers in the selection and design of EER models. Moreover, we make observations and in-depth analysis on the experiment results and identify current challenges in this community. We hope that our work will not only lower entry barriers for newcomers to EEG-based emotion recognition but also contribute to the standardization of research in this domain, fostering steady development. The library and source code are publicly available at https://github.com/XJTU-EEG/LibEER.
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 882-890
VidEvo: Evolving Video Editing through Exhaustive Temporal Modeling
Text-guided video editing (TGVE) has become a recent hotspot due to its entertainment value and practical applications. To reduce overhead, existing methods primarily extend from text-to-image diffusion models and typically involve reconstruction and editing phases. However, challenges persist, particularly in enhancing temporal consistency of a video while adhering to textual alignment requirements. A crucial factor leading to the aforementioned issue is the inadequate and implicit tuning of the attention module within existing methods, which is specifically designed to capture temporal information. In light of this, we introduce VidEvo, a novel one-shot video editing method that leverages explicit cues derived from the original video to enhance temporal modeling. By integrating null-video embedding (NVE) and window-frame attention (WFA) components, VidEvo facilitates the smooth and coherent generation of videos from global and local perspectives simultaneously. To be specific, NVE learns a set of multi-scale temporal embeddings within the visual space during the reconstruction phase. These embeddings are subsequently directly injected into the attention module of the editing phase, explicitly augmenting the temporal consistency of the entire video. On the other hand, WFA enhances local temporal modeling by dynamically optimizing attention mechanisms between adjacent frames, which improves temporal coherence with reduced computational costs. Experimental evaluations show that VidEvo enhances frame-to-frame temporal consistency. Ablation studies confirm NVE and WFA’s effectiveness and their plug-and-play capability with other methods.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 882-890
Open AccessVidEvo: Evolving Video Editing through Exhaustive Temporal Modeling
Text-guided video editing (TGVE) has become a recent hotspot due to its entertainment value and practical applications. To reduce overhead, existing methods primarily extend from text-to-image diffusion models and typically involve reconstruction and editing phases. However, challenges persist, particularly in enhancing temporal consistency of a video while adhering to textual alignment requirements. A crucial factor leading to the aforementioned issue is the inadequate and implicit tuning of the attention module within existing methods, which is specifically designed to capture temporal information. In light of this, we introduce VidEvo, a novel one-shot video editing method that leverages explicit cues derived from the original video to enhance temporal modeling. By integrating null-video embedding (NVE) and window-frame attention (WFA) components, VidEvo facilitates the smooth and coherent generation of videos from global and local perspectives simultaneously. To be specific, NVE learns a set of multi-scale temporal embeddings within the visual space during the reconstruction phase. These embeddings are subsequently directly injected into the attention module of the editing phase, explicitly augmenting the temporal consistency of the entire video. On the other hand, WFA enhances local temporal modeling by dynamically optimizing attention mechanisms between adjacent frames, which improves temporal coherence with reduced computational costs. Experimental evaluations show that VidEvo enhances frame-to-frame temporal consistency. Ablation studies confirm NVE and WFA’s effectiveness and their plug-and-play capability with other methods.
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (9) , 16435-16448
A Unified Optimal Transport Framework for Cross-Modal Retrieval With Noisy Labels
Cross-modal retrieval (CMR) aims to establish interaction between different modalities, among which supervised CMR is emerging due to its flexibility in learning semantic category discrimination. Despite the remarkable performance of previous supervised CMR methods, much of their success can be attributed to the well-annotated data. However, even for unimodal data, precise annotation is expensive and time-consuming, and it becomes more challenging with the multimodal scenario. In practice, massive multimodal data are collected from the Internet with coarse annotation, which inevitably introduces noisy labels. Training with such misleading labels would bring two key challenges—enforcing the multimodal samples to align incorrect semantics and widen the heterogeneous gap, resulting in poor retrieval performance. To tackle these challenges, this work proposes UOT-RCL, a unified framework based on optimal transport (OT) for robust CMR. First, we propose a semantic alignment based on partial OT to progressively correct the noisy labels, where a novel cross-modal consistent cost function is designed to blend different modalities and provide precise transport cost. Second, to narrow the discrepancy in multimodal data, an OT-based relation alignment is proposed to infer the semantic-level cross-modal matching. Both of these components leverage the inherent correlation among multimodal data to facilitate effective cost function. The experiments on three widely used CMR datasets demonstrate that our UOT-RCL surpasses the state-of-the-art approaches and significantly improves the robustness against noisy labels.
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (9) , 16435-16448
A Unified Optimal Transport Framework for Cross-Modal Retrieval With Noisy Labels
Cross-modal retrieval (CMR) aims to establish interaction between different modalities, among which supervised CMR is emerging due to its flexibility in learning semantic category discrimination. Despite the remarkable performance of previous supervised CMR methods, much of their success can be attributed to the well-annotated data. However, even for unimodal data, precise annotation is expensive and time-consuming, and it becomes more challenging with the multimodal scenario. In practice, massive multimodal data are collected from the Internet with coarse annotation, which inevitably introduces noisy labels. Training with such misleading labels would bring two key challenges—enforcing the multimodal samples to align incorrect semantics and widen the heterogeneous gap, resulting in poor retrieval performance. To tackle these challenges, this work proposes UOT-RCL, a unified framework based on optimal transport (OT) for robust CMR. First, we propose a semantic alignment based on partial OT to progressively correct the noisy labels, where a novel cross-modal consistent cost function is designed to blend different modalities and provide precise transport cost. Second, to narrow the discrepancy in multimodal data, an OT-based relation alignment is proposed to infer the semantic-level cross-modal matching. Both of these components leverage the inherent correlation among multimodal data to facilitate effective cost function. The experiments on three widely used CMR datasets demonstrate that our UOT-RCL surpasses the state-of-the-art approaches and significantly improves the robustness against noisy labels.
- Open Access
MIND-EEG: Multi-granularity Integration Network with Discrete Codebook for EEG-based Emotion Recognition
Emotion recognition using electroencephalogram (EEG) signals has broad potential across various domains. EEG signals have ability to capture rich spatial information related to brain activity, yet effectively modeling and utilizing these spatial relationships remains a challenge. Existing methods struggle with simplistic spatial structure modeling, failing to capture complex node interactions, and lack generalizable spatial connection representations, failing to balance the dynamic nature of brain networks with the need for discriminative and generalizable features. To address these challenges, we propose the Multi-granularity Integration Network with Discrete Codebook for EEG-based Emotion Recognition (MIND-EEG). The framework employs a multi-granularity approach, integrating global and regional spatial information through a Global State Encoder, an Intra-Regional Functionality Encoder, and an Inter-Regional Interaction Encoder to comprehensively model brain activity. Additionally, we introduce a discrete codebook mechanism for constructing network structures via vector quantization, ensuring compact and meaningful brain network representations while mitigating over-smoothing and enhancing model generalization. The proposed framework effectively captures the dynamic and diverse nature of EEG signals, enabling robust emotion recognition. Extensive comparisons and analyses demonstrate the effectiveness of MIND-EEG, and the source code is publicly available at https://anonymous.4open.science/r/MIND_EEG.
Open AccessMIND-EEG: Multi-granularity Integration Network with Discrete Codebook for EEG-based Emotion Recognition
Emotion recognition using electroencephalogram (EEG) signals has broad potential across various domains. EEG signals have ability to capture rich spatial information related to brain activity, yet effectively modeling and utilizing these spatial relationships remains a challenge. Existing methods struggle with simplistic spatial structure modeling, failing to capture complex node interactions, and lack generalizable spatial connection representations, failing to balance the dynamic nature of brain networks with the need for discriminative and generalizable features. To address these challenges, we propose the Multi-granularity Integration Network with Discrete Codebook for EEG-based Emotion Recognition (MIND-EEG). The framework employs a multi-granularity approach, integrating global and regional spatial information through a Global State Encoder, an Intra-Regional Functionality Encoder, and an Inter-Regional Interaction Encoder to comprehensively model brain activity. Additionally, we introduce a discrete codebook mechanism for constructing network structures via vector quantization, ensuring compact and meaningful brain network representations while mitigating over-smoothing and enhancing model generalization. The proposed framework effectively captures the dynamic and diverse nature of EEG signals, enabling robust emotion recognition. Extensive comparisons and analyses demonstrate the effectiveness of MIND-EEG, and the source code is publicly available at https://anonymous.4open.science/r/MIND_EEG.