Research output

Publications

Selected journal articles, conference papers, preprints and datasets from the lab. Use the filters to explore the collection.

32records in the current catalogue

32 publications

CLARA framework: utterance-aligned clips with audio, visual and text encoders, a mixture-of-experts router, local-global contrastive learning and VLM-derived rationale tokens fused by a gated transformer.2026

CLARA: Clip-Level Multimodal Alignment with VLM-Derived Rationales for Hateful Video Detection

Yuchen Zhang, Shuang Dai, Zeyu Fu, Yunfei Long, Ravi Shekhar, Haralambos Mouratidis

ACM International Conference on Multimedia (ACM MM), 2026

Comparison of training and test worst-class accuracy for long-tailed recognition methods.2026
ConferenceOral PresentationTrustworthy AI

Confusion-Aware Spectral Regularizer for Long-Tailed Recognition

Ziquan Zhu, Gaojie Jin, Hanruo Zhu, Si-Yuan Lu, Yunxiao Zhang, Zeyu Fu, Ronghui Mu, Guoqiang Zhang, Zhao Sun, Xia Yuhang, Jiaxing Shang, Xiang Li, Lu Liu, Tianjin Huang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Overview of the CPR framework: a shared encoder, perceptual state, policy network and prediction head applied over chained coarse-to-fine crops.2026

CPR: Chained Perceptual Refinement for Coarse-to-Fine Medical Image Classification

Si-Yuan Lu, Hanruo Zhu, Ziquan Zhu, Gaojie Jin, Zeyu Fu, Lu Yin, Ke Li, Lu Liu, Tianjin Huang

Medical Image Computing and Computer Assisted Intervention (MICCAI), 2026

CFT-NET and progressive visual-semantic adaptation framework for aligning EEG signals with visual representations.2026

Cross-Modal Progressive Modeling for Neuro-Visual Representation Learning

Yueming Sun, Jiyao Pu, Kaili Sun, Zeyu Fu, Haoran Duan, Yang Long

Neurocomputing, 2026

Overview of the EASM-based change detection framework and the internal edge extraction, masking and reconstruction workflow.2026

Enhancing Remote Sensing Change Detection via Masked Edge Reconstruction

Shuaiyu Chen, Fu Wang, Tianjin Huang, Xiang Li, Siyang Song, Guangliang Cheng, Chunbo Luo, Zeyu Fu

WACV 2026 Workshops (CV4EO), 2026

FairMT framework for fairness-aware heterogeneous multi-task learning.2026
ConferenceTrustworthy AI

FairMT: Fairness for Heterogeneous Multi-Task Learning

Guanyu Hu, Tangzheng Lian, Na Yan, Dimitrios Kollias, Xinyu Yang, Oya Celiktutan, Siyang Song, Zeyu Fu

Advances in Neural Information Processing Systems (NeurIPS), 2026

Generalist–specialist transfer-learning workflow across ten cities in South West England.2026

Generalist–specialist transfer learning for cross-city spatial generalization in pluvial flood prediction

Zhufeng Li, Zeyu Fu, Guangtao Fu

Water Research, 2026

Overview of the GraphRAG-Rad framework: latent visual-semantic retrieval, knowledge-grounded visual encoding, multi-hop reasoning and graph-gated fusion for report generation.2026

GraphRAG-Rad: Concept-Aware Radiology Report Generation via Latent Visual-Semantic Retrieval

Faezeh Safari, Hang Dong, Zeyu Fu, Aline Villavicencio

EACL 2026 Student Research Workshop, 2026

Overview of the two-stage Localize-Then-Decide guarantees framework.2026
ConferenceTrustworthy AI

Localize-Then-Decide Guarantees for LLM Judgments

Xinyu Li, Yi Zhou, Guanqun Cao, Zeyu Fu, Tianjin Huang, Gaojie Jin

Findings of the Association for Computational Linguistics: EMNLP, 2026

MambaMPD architecture combining a Mamba encoder with frequency-aware augmentation and edge-guided attention.2026

MambaMPD: A Mamba-Driven Segmentation Framework for Marine Pollution Detection from Remote Sensing Imagery

Shuaiyu Chen, Wei Han, Peng Ren, Chunbo Luo, Zeyu Fu

GIScience & Remote Sensing, 2026

Pipeline of MReactor: multi-modal behaviour perception, hierarchical cognition disentanglement and multiple facial reaction generation.2026

MReactor: Offline Multiple Appropriate Facial Reaction Generation with Hierarchical Cognitive Disentanglement

Jiachen Luo, Jiajun He, Shuai Shen, Lin Wang, Huy Phan, Joshua Reiss, Lin Haijun, Bjoern Schuller, Zeyu Fu, Siyang Song

CVPR 2026 Findings, 2026

Overview of MultiHateLoc: modality-aware temporal encoding, dynamic cross-modal fusion and modality-wise top-K MIL.2026

MultiHateLoc: Towards Temporal Localisation of Multimodal Hate Content in Online Videos

Qiyue Sun, Tailin Chen, Yinghui Zhang, Yuchen Zhang, Jiangbei Yue, Jianbo Jiao, Zeyu Fu

Proceedings of the ACM Web Conference (The Web Conference), 2026

OilSAM2 framework with hierarchical texture, structure and semantic memory for SAR oil-spill segmentation.2026

OilSAM2: Memory-Augmented SAM2 for Scalable SAR Oil Spill Detection

Shuaiyu Chen, Ming Yin, Peng Ren, Chunbo Luo, Zeyu Fu

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026

Training pipeline and architecture of Omni-Fake-R1 for unified deepfake detection, localisation and explanation.2026

Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection

Tianxiao Li, Zhenglin Huang, Haiquan Wen, Yiwei He, Xinze Li, Bingyu Zhu, Wuhui Duan, Congang Chen, Zeyu Fu, Yi Dong, Baoyuan Wu, Jason Li, Guangliang Cheng

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Framework for 3D anomaly detection: multi-view generation, registration pipeline and anomaly scoring.2026

Probing 3D Anomalies via Multi-View Registration and Dual-Residual Analysis

Yuxing Yang, Zeyu Fu, Yang Li, Liewei Wang, Siyue Yu, Jimin Xiao

Neurocomputing, 2026

Architecture of RAMF, combining local-global context fusion, semantic cross attention and VLM adversarial reasoning.2026

Reasoning-Aware Multimodal Fusion for Hateful Video Detection

Shuonan Yang, Tailin Chen, Jiangbei Yue, Guangliang Cheng, Jianbo Jiao, Zeyu Fu

Transactions on Machine Learning Research (TMLR), 2026

Overview of ReGround-Surg: text-guided reliability gate, gated side adapter and RW-V2T attention for detection, followed by SAM2 tracking.2026
ConferenceOral Presentation (2.8%)AI for Healthcare

ReGround-Surg: Reliability-Guided Anchor Grounding for Referring Surgical Video Segmentation

Jiaxin Wen, Ming Yin, Lu Liu, Zeyu Fu

Pattern Recognition and Computer Vision (PRCV), 2026

Overview of the MARS multi-stage adversarial reasoning framework for hateful video detection.2026

Training-Free and Interpretable Hateful Video Detection via Multi-stage Adversarial Reasoning

Shuonan Yang, Yuchen Zhang, Zeyu Fu

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026

2025

Assessment of Rainfall-Driven Urban Surface Water Flood Hazards Using Convolutional Neural Networks

Zhufeng Li, Haixing Liu, Zeyu Fu, Guangtao Fu

Journal of Flood Risk Management, 2025

Distributions of hateful segment lengths and proportions in the DeHate dataset.2025

DeHate: A Holistic Hateful Video Dataset for Explicit and Implicit Hate Detection

Yuchen Zhang, Tailin Chen, Jiangbei Yue, Yueming Sun, Rahul Singh, Jianbo Jiao, Zeyu Fu

ACM Multimedia 2025, 2025

2025

Discriminator-Guided Generative Adversarial Networks for Urban Flood Prediction

Zhufeng Li, Zeyu Fu, Qian Li, Guangtao Fu

Water Resources Research, 2025

Marine-pollution segmentation network with self-supervised boundary-awareness blocks across encoder stages.2025

Enhancing Marine Pollution Detection in Remote Sensing via Self-Supervised Boundary Awareness

Shuaiyu Chen, Chunbo Luo, Peng Ren, Zeyu Fu

BMVC 2025 MVEO Workshop, 2025

2025

Integrating Semantic, Sentiment, and Object-Level Cues for Multimodal Video-Based Fake News Detection

Ruby Ham, Yuchen Zhang, Zeyu Fu

ACM DHOW 2025, 2025

Architecture of MA-SAM2 with its memory-augmented strategy of context-aware and occlusion-resilient memories.2025
ConferenceOral PresentationAI for Healthcare

Memory-Augmented SAM2 for Training-Free Surgical Video Segmentation

Ming Yin, Fu Wang, Xujiong Ye, Yanda Meng, Zeyu Fu

Medical Image Computing and Computer Assisted Intervention (MICCAI), 2025

Dual-stream graph neural network architecture for instance-aware multimodal hateful-video detection.2025

Multimodal Hate Detection Using Dual-Stream Graph Neural Networks

Jiangbei Yue, Shuonan Yang, Tailin Chen, Jianbo Jiao, Zeyu Fu

British Machine Vision Conference (BMVC), 2025

Architecture of OSDMamba: a VMamba encoder of VSS blocks and an asymmetric decoder with ConvSSM and deep supervision.2025

OSDMamba: Enhancing Oil Spill Detection from Remote Sensing Images Using Selective State Space Model

Shuaiyu Chen, Fu Wang, Peng Ren, Chunbo Luo, Zeyu Fu

IEEE Geoscience and Remote Sensing Letters, 2025

2025

Pose-Oriented Scene-Adaptive Matching for Abnormal Event Detection

Yuxing Yang, Leiyu Xie, Zeyu Fu, Jiawei Yan, Syed Mohsen Naqvi

Neurocomputing, 611:128673, 2025

2025

PySimPace v2.0: An Easy-to-Use Simulation Tool with Machine Learning Pipelines for Realistic MRI Motion Artifact Generation

Snehil Kumar, Neil Vaughan, Zeyu Fu, Heather Wilson

ACM Multimedia 2025 Open Source Track, 2025

Research pipeline for analysing temporal label noise in hateful-video classification.2025

Revealing Temporal Label Noise in Multimodal Hateful Video Classification

Shuonan Yang, Tailin Chen, Rahul Singh, Jiangbei Yue, Jianbo Jiao, Zeyu Fu

ACM Multimedia Workshop on Multimodal Understanding for a Safer Web, 2025

A Black-Box Evaluation Framework for Semantic Robustness in Bird's Eye View Detection

Fu Wang, Yanghao Zhang, Xiangyu Yin, Guangliang Cheng, Zeyu Fu, Xiaowei Huang, Wenjie Ruan

arXiv preprint, 2024

Position and Orientation Aware One-Shot Learning for Medical Action Recognition from Signal Data

Leiyu Xie, Yuxing Yang, Zeyu Fu, Syed Mohsen Naqvi

IEEE Transactions on Multimedia, 2024

2023

Abnormal Event Detection for Video Surveillance Using an Enhanced Two-Stream Fusion Method

Yuxing Yang, Zeyu Fu, Syed Mohsen Naqvi

Neurocomputing, 553:126561, 2023