MIL UK - Publications

Publications

Pose-Oriented Scene-Adaptive Matching for Abnormal Event Detection

Publication Date: Jan 2025

Authors: Yang Y, Xie L, Fu Z, Yan J, Naqvi SM

Tags: Journal Article, Neurocomputing, 611:128673, Elsevier

View Paper View Project Page

              @article{YANG2025128673,
              title = {Pose-oriented scene-adaptive matching for abnormal event detection},
              journal = {Neurocomputing},
              volume = {611},
              pages = {128673},
              year = {2025},
              issn = {0925-2312},
              doi = {https://doi.org/10.1016/j.neucom.2024.128673},
              url = {https://www.sciencedirect.com/science/article/pii/S0925231224014449},
              author = {Yuxing Yang and Leiyu Xie and Zeyu Fu and Jiawei Yan and Syed Mohsen Naqvi},
              keywords = {Abnormal event detection, Scene-adaptive, Pose estimation, Object detection, Graph convolutions}}

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

Publication Date: 24 Dec 2024

Authors: Xie L, Yang Y, Fu Z, Naqvi SM

Tags: Journal Article, Transactions on Multimedia, PP(99):1-14, Institute of Electrical and Electronics Engineers (IEEE)

View Paper View Project Page

              @ARTICLE{10814994,
                author={Xie, Leiyu and Yang, Yuxing and Fu, Zeyu and Naqvi, Syed Mohsen},
                journal={IEEE Transactions on Multimedia}, 
                title={Position and Orientation Aware One-Shot Learning for Medical Action Recognition from Signal Data}, 
                year={2024},
                volume={},
                number={},
                pages={1-14},
                keywords={Feature extraction;Biomedical imaging;Skeleton;One shot learning;Training;Human activity recognition;Privacy;Data models;Protection;Data privacy;One-shot learning;medical action recognition;attention mechanism;feature fusion;healthcare},
                doi={10.1109/TMM.2024.3521703}}

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

Publication Date: 18 Dec 2024

Authors: Wang F, Zhang Y, Yin X, Cheng G, Fu Z, Huang X, Ruan W

Tags: Preprint

View Paper

              @misc{wang2024blackboxevaluationframeworksemantic,
                title={A Black-Box Evaluation Framework for Semantic Robustness in Bird's Eye View Detection}, 
                author={Fu Wang and Yanghao Zhang and Xiangyu Yin and Guangliang Cheng and Zeyu Fu and Xiaowei Huang and Wenjie Ruan},
                year={2024},
                eprint={2412.13913},
                archivePrefix={arXiv},
                primaryClass={cs.CV},
                url={https://arxiv.org/abs/2412.13913},}

GlobalMapNet: An Online Framework for Vectorized Global HD Map Construction

Publication Date: 16 Sep 2024

Authors: Shi A, Cai Y, Chen X, Pu J, Fu Z, Lu H

Tags: Preprint

View Paper

              @misc{shi2024globalmapnetonlineframeworkvectorized,
                title={GlobalMapNet: An Online Framework for Vectorized Global HD Map Construction}, 
                author={Anqi Shi and Yuze Cai and Xiangyu Chen and Jian Pu and Zeyu Fu and Hong Lu},
                year={2024},
                eprint={2409.10063},
                archivePrefix={arXiv},
                primaryClass={cs.CV},
                url={https://arxiv.org/abs/2409.10063},}

Abnormal event detection for video surveillance using an enhanced two-stream fusion method

Publication Date: Oct 2023

Authors: Yang Y, Fu Z, Naqvi SM

Tags: Journal Article, Neurocomputing, 553:126561, Elsevier

View Paper

              @article{YANG2023126561,
                title = {Abnormal event detection for video surveillance using an enhanced two-stream fusion method},
                journal = {Neurocomputing},
                volume = {553},
                pages = {126561},
                year = {2023},
                issn = {0925-2312},
                doi = {https://doi.org/10.1016/j.neucom.2023.126561},
                url = {https://www.sciencedirect.com/science/article/pii/S0925231223006847},
                author = {Yuxing Yang and Zeyu Fu and Syed Mohsen Naqvi},
                keywords = {Abnormal event detection, Pose estimation, Optical flow, Object detection, Graph convolutional neural network, Adversarial learning, Data fusion},}

One-Shot Medical Action Recognition With A Cross-Attention Mechanism And Dynamic Time Warping

Publication Date: 10 Jun 2023

Authors: Xie L, Yang Y, Fu Z, Naqvi SM

Tags: Conference, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 00:1-5, Institute of Electrical and Electronics Engineers (IEEE)

View Paper

              @INPROCEEDINGS{10097186,
                author={Xie, Leiyu and Yang, Yuxing and Fu, Zeyu and Naqvi, Syed Mohsen},
                booktitle={ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
                title={One-Shot Medical Action Recognition With A Cross-Attention Mechanism And Dynamic Time Warping}, 
                year={2023},
                volume={},
                number={},
                pages={1-5},
                keywords={Measurement;Codes;Transforms;Medical services;Signal processing;Image representation;Skeleton;one-shot learning;healthcare;crossattention;medical action classification;signal representation},
                doi={10.1109/ICASSP49357.2023.10097186}}

Projects

Holistic Hateful Video Detection and Localisation via Multi-Modal Graph Learning

Partners: The Alan Turing Insitute and Jianbo Jiao

Social media companies like YouTube and Facebook employ human moderators to review user-flagged videos before they escalate and cause long-term harm to society. However, given the sheer volume of daily uploads, ensuring compliance with established policies becomes challenging. Smaller platforms with limited resources may struggle to afford human moderators, thereby making affordable and automated hateful content detection solutions highly desirable. Current automated approaches mainly rely on textual media or features for identifying hateful content, with fewer studies focused on the analysis of videos. This research domain presents its distinct set of challenges. In this project, we will try to alliviate the challenges via multi-modal graph learning.