Hongliu Li
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
Hongliu Li has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
Weiguo Song
State Key Laboratory of Fire Science, University of Science and Technology of China, Hefei, People’s Republic of China
9 shared publicationsJun Zhang
6 shared publications- Richard Kwowk Kit Yuen
Department of Architecture and Civil Engineering, City University of Hong Kong, Kowloon Tong, Hong Kong
4 shared publications - Jiahua Dong
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
3 shared publications - Jun Zhang
State Key Laboratory of Fire Science, University of Science and Technology of China, Hefei, China
3 shared publications Long Xia
State Key Laboratory of Fire Science, University of Science and Technology of China, Hefei, People’s Republic of China
3 shared publications
Latest Publications
- 8 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-18
Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization
Custom diffusion models (CDMs) have garnered significant interest owing to their remarkable capacity for generating personalized concepts. However, the majority of CDMs unrealistically presume that the user's collection of personalized concepts is static and incapable of incremental growth over time. Furthermore, they exhibit significant catastrophic forgetting and concept neglect of previously learned concepts when incrementally learning a sequence of new ones. To resolve the above challenges, we develop a novel Continually Customizable Diffusion Model (CCDM), enabling users to perform concept-incremental versatile customization. Specifically, we design an attribute-decoupled LoRA (AD-LoRA) module and a relevance-guided AD-LoRA aggregation strategy to mitigate catastrophic forgetting. They can preserve concept-specific attributes of each task and leverage beneficial inter-task correlations to enhance the continual learning of new customization tasks. Additionally, to address the challenge of concept neglect, we propose a controllable regional context synthesis strategy that performs multi-concept composition in alignment with user-provided conditions. This strategy enhances the overall consistency in multi-concept synthesis by guaranteeing semantic independence between user-defined regions and their smooth boundary transitions. Experiments show our CCDM exhibits significant improvements over baseline methods.
- 8 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-18
Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization
Custom diffusion models (CDMs) have garnered significant interest owing to their remarkable capacity for generating personalized concepts. However, the majority of CDMs unrealistically presume that the user's collection of personalized concepts is static and incapable of incremental growth over time. Furthermore, they exhibit significant catastrophic forgetting and concept neglect of previously learned concepts when incrementally learning a sequence of new ones. To resolve the above challenges, we develop a novel Continually Customizable Diffusion Model (CCDM), enabling users to perform concept-incremental versatile customization. Specifically, we design an attribute-decoupled LoRA (AD-LoRA) module and a relevance-guided AD-LoRA aggregation strategy to mitigate catastrophic forgetting. They can preserve concept-specific attributes of each task and leverage beneficial inter-task correlations to enhance the continual learning of new customization tasks. Additionally, to address the challenge of concept neglect, we propose a controllable regional context synthesis strategy that performs multi-concept composition in alignment with user-provided conditions. This strategy enhances the overall consistency in multi-concept synthesis by guaranteeing semantic independence between user-defined regions and their smooth boundary transitions. Experiments show our CCDM exhibits significant improvements over baseline methods.
- Open Access
- 8 January 2026
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 685
Impact of the caregiver-to-resident ratio on evacuation efficiency in nursing homes: A simulation-based study
- 8 January 2026
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 685
Open AccessImpact of the caregiver-to-resident ratio on evacuation efficiency in nursing homes: A simulation-based study
- 12 March 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 215, 107986
A review on the use of top-view surveillance videos for pedestrian detection, tracking and behavior recognition across public spaces
- 12 March 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 215, 107986
A review on the use of top-view surveillance videos for pedestrian detection, tracking and behavior recognition across public spaces
- 11 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (11) , 4041-4054
Prototype Correlation Matching and Class- Relation Reasoning for Few-Shot Medical Image Segmentation
Few-shot medical image segmentation has achieved great progress in improving accuracy and efficiency of medical analysis in the biomedical imaging field. However, most existing methods cannot explore inter-class relations among base and novel medical classes to reason unseen novel classes. Moreover, the same kind of medical class has large intra-class variations brought by diverse appearances, shapes and scales, thus causing ambiguous visual characterization to degrade generalization performance of these existing methods on unseen novel classes. To address the above challenges, in this paper, we propose a Prototype correlation Matching and Class-relation Reasoning (i.e., PMCR) model. The proposed model can effectively mitigate false pixel correlation matches caused by large intra-class variations while reasoning inter-class relations among different medical classes. Specifically, in order to address false pixel correlation match brought by large intra-class variations, we propose a prototype correlation matching module to mine representative prototypes that can characterize diverse visual information of different appearances well. We aim to explore prototypelevel rather than pixel-level correlation matching between support and query features via optimal transport algorithm to tackle false matches caused by intra-class variations. Meanwhile, in order to explore inter-class relations, we design a class-relation reasoning module to segment unseen novel medical objects via reasoning inter-class relations between base and novel classes. Such inter-class relations can be well propagated to semantic encoding of local query features to improve few-shot segmentation performance. Quantitative comparisons illustrates the large performance improvement of our model over other baseline methods.
- 11 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (11) , 4041-4054
Prototype Correlation Matching and Class- Relation Reasoning for Few-Shot Medical Image Segmentation
Few-shot medical image segmentation has achieved great progress in improving accuracy and efficiency of medical analysis in the biomedical imaging field. However, most existing methods cannot explore inter-class relations among base and novel medical classes to reason unseen novel classes. Moreover, the same kind of medical class has large intra-class variations brought by diverse appearances, shapes and scales, thus causing ambiguous visual characterization to degrade generalization performance of these existing methods on unseen novel classes. To address the above challenges, in this paper, we propose a Prototype correlation Matching and Class-relation Reasoning (i.e., PMCR) model. The proposed model can effectively mitigate false pixel correlation matches caused by large intra-class variations while reasoning inter-class relations among different medical classes. Specifically, in order to address false pixel correlation match brought by large intra-class variations, we propose a prototype correlation matching module to mine representative prototypes that can characterize diverse visual information of different appearances well. We aim to explore prototypelevel rather than pixel-level correlation matching between support and query features via optimal transport algorithm to tackle false matches caused by intra-class variations. Meanwhile, in order to explore inter-class relations, we design a class-relation reasoning module to segment unseen novel medical objects via reasoning inter-class relations between base and novel classes. Such inter-class relations can be well propagated to semantic encoding of local query features to improve few-shot segmentation performance. Quantitative comparisons illustrates the large performance improvement of our model over other baseline methods.
- 20 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (4) , 2054-2070
No One Left Behind: Real-World Federated Class-Incremental Learning
Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novel L ocal- G lobal A nti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods.
- 20 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (4) , 2054-2070
No One Left Behind: Real-World Federated Class-Incremental Learning
Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novel L ocal- G lobal A nti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3319-3329
Task Relation Distillation and Prototypical Pseudo Label for Incremental Named Entity Recognition
Incremental Named Entity Recognition (INER) involves the sequential learning of new entity types without accessing the training data of previously learned types. However, INER faces the challenge of catastrophic forgetting specific for incremental learning, further aggravated by background shift (i.e., old and future entity types are labeled as the non-entity type in the current task). To address these challenges, we propose a method called task Relation Distillation and Prototypical pseudo label (RDP) for INER. Specifically, to tackle catastrophic forgetting, we introduce a task relation distillation scheme that serves two purposes: 1) ensuring inter-task semantic consistency across different incremental learning tasks by minimizing inter-task relation distillation loss, and 2) enhancing the model's prediction confidence by minimizing intra-task self-entropy loss. Simultaneously, to mitigate background shift, we develop a prototypical pseudo label strategy that distinguishes old entity types from the current non-entity type using the old model. This strategy generates high-quality pseudo labels by measuring the distances between token embeddings and type-wise prototypes. We conducted extensive experiments on ten INER settings of three benchmark datasets (i.e., CoNLL2003, I2B2, and OntoNotes5). The results demonstrate that our method achieves significant improvements over the previous state-of-the-art methods, with an average increase of 6.08% in Micro F1 score and 7.71% in Macro F1 score.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3319-3329
Open AccessTask Relation Distillation and Prototypical Pseudo Label for Incremental Named Entity Recognition
Incremental Named Entity Recognition (INER) involves the sequential learning of new entity types without accessing the training data of previously learned types. However, INER faces the challenge of catastrophic forgetting specific for incremental learning, further aggravated by background shift (i.e., old and future entity types are labeled as the non-entity type in the current task). To address these challenges, we propose a method called task Relation Distillation and Prototypical pseudo label (RDP) for INER. Specifically, to tackle catastrophic forgetting, we introduce a task relation distillation scheme that serves two purposes: 1) ensuring inter-task semantic consistency across different incremental learning tasks by minimizing inter-task relation distillation loss, and 2) enhancing the model's prediction confidence by minimizing intra-task self-entropy loss. Simultaneously, to mitigate background shift, we develop a prototypical pseudo label strategy that distinguishes old entity types from the current non-entity type using the old model. This strategy generates high-quality pseudo labels by measuring the distances between token embeddings and type-wise prototypes. We conducted extensive experiments on ten INER settings of three benchmark datasets (i.e., CoNLL2003, I2B2, and OntoNotes5). The results demonstrate that our method achieves significant improvements over the previous state-of-the-art methods, with an average increase of 6.08% in Micro F1 score and 7.71% in Macro F1 score.
- 24 February 2023
- Published by Taylor & Francis in Transportmetrica A: Transport Science
- Vol. 20 (3)
Influence of movement motivations on spatial and temporal features: a case study of preschool children passing through a right-angled corridor
Pedestrian dynamics of preschool children in facilities has become a rapidly growing research topic due to its significant implications for children’s safety. This work investigates the movement characteristics of 40 preschool children passing through a 1.0 m wide right-angled corridor under low and high motivations. Under low and high motivation, preschool children were asked to walk through the corridor as normal and run through the corridor quickly as if in an emergency, respectively. The fundamental diagrams, velocity directions, passing positions, and spatial distributions are studied. Individual speed decreases with increasing density, both in normal and emergency conditions. In the turning region, children prefer running near the inner boundaries but walking along the outer boundaries. Running children keep a greater distance both from the boundaries and from other children, compared to walking children. The findings could help enhance the comprehension of the movement characteristics of preschool children. Highlights
- 24 February 2023
- Published by Taylor & Francis in Transportmetrica A: Transport Science
- Vol. 20 (3)
Influence of movement motivations on spatial and temporal features: a case study of preschool children passing through a right-angled corridor
Pedestrian dynamics of preschool children in facilities has become a rapidly growing research topic due to its significant implications for children’s safety. This work investigates the movement characteristics of 40 preschool children passing through a 1.0 m wide right-angled corridor under low and high motivations. Under low and high motivation, preschool children were asked to walk through the corridor as normal and run through the corridor quickly as if in an emergency, respectively. The fundamental diagrams, velocity directions, passing positions, and spatial distributions are studied. Individual speed decreases with increasing density, both in normal and emergency conditions. In the turning region, children prefer running near the inner boundaries but walking along the outer boundaries. Running children keep a greater distance both from the boundaries and from other children, compared to walking children. The findings could help enhance the comprehension of the movement characteristics of preschool children. Highlights
- 1 March 2021
- Published by Elsevier in Fire Safety Journal
- Vol. 120
A comparative study on the bottleneck pedestrian flow under different movement motivations
- 1 March 2021
- Published by Elsevier in Fire Safety Journal
- Vol. 120
A comparative study on the bottleneck pedestrian flow under different movement motivations
- 17 November 2020
- Published by Springer Nature
- p. 315-320
Experimental Study on Pedestrian Flow Under Different Age Groups and Movement Motivations
- 17 November 2020
- Published by Springer Nature
- p. 315-320
Experimental Study on Pedestrian Flow Under Different Age Groups and Movement Motivations
- 17 November 2020
- Published by Springer Nature
- p. 159-164
Evacuation Characteristics of Students Passing Through Bottlenecks
- 17 November 2020
- Published by Springer Nature
- p. 159-164
Evacuation Characteristics of Students Passing Through Bottlenecks