publications | Yuhang Ming

2026

Neurocomputing

D3FlowSLAM: Self-supervised dynamic SLAM with flow motion decomposition and DINO guidance

Xingyuan Yu, Weicai Ye, Xiyue Guo, Yuhang Ming, and 4 more authors

Neurocomputing, 2026

@article{Yu2026d3flowslam,
  title = {D3FlowSLAM: Self-supervised dynamic SLAM with flow motion decomposition and DINO guidance},
  journal = {Neurocomputing},
  volume = {677},
  pages = {133023},
  year = {2026},
  issn = {0925-2312},
  doi = {https://doi.org/10.1016/j.neucom.2026.133023},
  url = {https://www.sciencedirect.com/science/article/pii/S0925231226004200},
  author = {Yu, Xingyuan and Ye, Weicai and Guo, Xiyue and Ming, Yuhang and Li, Jinyu and Bao, Hujun and Cui, Zhaopeng and Zhang, Guofeng},
  keywords = {Self-supervised learning, Dynamic SLAM, Flow decomposition, DINO model},
}

CoDy
Uncertainty-aware human–machine collaboration in Camouflaged Object Detection

Ziyue Yang, Kehan Wang, Yuhang Ming, Han Yang, and 3 more authors

Cognitive Neurodynamics, Feb 2026

Abs Bib

Camouflaged Object Detection (COD), the task of identifying objects concealed within their environments, has seen rapid growth due to its wide range of practical applications. We propose a human–machine collaboration framework for COD, leveraging the complementary strengths of computer vision (CV) models and noninvasive brain-computer interfaces (BCIs). Our approach introduces a multiview backbone to estimate uncertainty in CV predictions, utilizes this uncertainty during training to improve efficiency, and defers low-confidence cases to human evaluation via RSVP-based BCIs during testing for more reliable decision-making. Evaluated on the CAMO dataset, our framework achieves state-of-the-art results with an average improvement of 4.56% in balanced accuracy (BA) and 3.66% in the F1 score. For the best-performing participants, improvements reached 7.6% in BA and 6.66% in the F1 score. Training analysis showed a strong correlation between confidence and precision, while ablation studies confirmed the effectiveness of our training policy and human–machine collaboration strategy. This work reduces human cognitive load, improves system reliability, and provides a foundation for advancements in real-world COD applications and human-computer interaction. Our code and data are available at: https://github.com/ziyuey/Uncertainty-aware-human-machine-collaboration-in-camouflaged-object-identification.
@article{Yang2026uncertaintyaware, author = {Yang, Ziyue and Wang, Kehan and Ming, Yuhang and Yang, Han and Chen, Qiong and Peng, Yong and Kong, Wanzeng}, title = {Uncertainty-aware human--machine collaboration in Camouflaged Object Detection}, journal = {Cognitive Neurodynamics}, year = {2026}, month = feb, day = {03}, volume = {20}, number = {1}, pages = {45}, issn = {1871-4099}, doi = {10.1007/s11571-025-10407-x}, url = {https://doi.org/10.1007/s11571-025-10407-x}, }

2025

SLC^2-SLAM: Semantic-Guided Loop Closure Using Shared Latent Code for NeRF SLAM

Yuhang Ming, Di Ma, Weichen Dai, Han Yang, and 3 more authors

IEEE Robotics and Automation Letters, Feb 2025

Bib Code

@article{Ming2025slc2slam,
  author = {Ming, Yuhang and Ma, Di and Dai, Weichen and Yang, Han and Fan, Rui and Zhang, Guofeng and Kong, Wanzeng},
  journal = {IEEE Robotics and Automation Letters},
  title = {SLC$^{2}$-SLAM: Semantic-Guided Loop Closure Using Shared Latent Code for NeRF SLAM},
  year = {2025},
  volume = {10},
  number = {5},
  pages = {4978-4985},
  keywords = {Simultaneous localization and mapping;Neural radiance field;Codes;Tracking loops;Semantics;Feature extraction;Encoding;Optimization;Artificial intelligence;Accuracy;SLAM;loop detection;localization;semantic scene understanding},
  doi = {10.1109/LRA.2025.3553352},
}

VIPeR: Visual Incremental Place Recognition With Adaptive Mining and Continual Learning

Yuhang Ming, Minyang Xu, Xingrui Yang, Weicai Ye, and 4 more authors

IEEE Robotics and Automation Letters, Feb 2025

Bib Code Website

@article{Ming2025VIPeR,
  author = {Ming, Yuhang and Xu, Minyang and Yang, Xingrui and Ye, Weicai and Wang, Weihan and Peng, Yong and Dai, Weichen and Kong, Wanzeng},
  journal = {IEEE Robotics and Automation Letters},
  title = {VIPeR: Visual Incremental Place Recognition With Adaptive Mining and Continual Learning},
  year = {2025},
  volume = {10},
  number = {3},
  pages = {3038-3045},
  keywords = {Continuing education;Visualization;Training;Measurement;Atmospheric modeling;Adaptation models;Computational modeling;Data mining;Probabilistic logic;Image recognition;Localization;recognition;continual learning},
  doi = {10.1109/LRA.2025.3539093},
}

Benchmarking neural radiance fields for autonomous robots: An overview

Yuhang Ming, Xingrui Yang, Weihan Wang, Zheng Chen, and 3 more authors

Engineering Applications of Artificial Intelligence, Feb 2025

arXiv Bib

@article{Ming2025survey,
  title = {Benchmarking neural radiance fields for autonomous robots: An overview},
  journal = {Engineering Applications of Artificial Intelligence},
  volume = {140},
  pages = {109685},
  year = {2025},
  issn = {0952-1976},
  doi = {https://doi.org/10.1016/j.engappai.2024.109685},
  url = {https://www.sciencedirect.com/science/article/pii/S0952197624018438},
  author = {Ming, Yuhang and Yang, Xingrui and Wang, Weihan and Chen, Zheng and Feng, Jinglun and Xing, Yifan and Zhang, Guofeng},
}

App. Sci.

CriSALAD: Robust Visual Place Recognition Using Cross-Image Information and Optimal Transport Aggregation

Jinyi Xu, Yuhang Ming, Minyang Xu, Yaqi Fan, and 2 more authors

Applied Sciences, Feb 2025

Bib

@article{Xu2025crisalad,
  author = {Xu, Jinyi and Ming, Yuhang and Xu, Minyang and Fan, Yaqi and Zhang, Yuan and Kong, Wanzeng},
  title = {CriSALAD: Robust Visual Place Recognition Using Cross-Image Information and Optimal Transport Aggregation},
  journal = {Applied Sciences},
  volume = {15},
  year = {2025},
  number = {10},
  article-number = {5287},
  url = {https://www.mdpi.com/2076-3417/15/10/5287},
  issn = {2076-3417},
  doi = {10.3390/app15105287},
}

CVPR

Multi-Modal Synergistic Implicit Image Enhancement for Efficient Optical Flow Estimation

Weichen Dai, Hexing Wu, Xiaoyang Weng, Yuxin Zheng, and 2 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2025

Bib

@inproceedings{Dai2025CVPR,
  author = {Dai, Weichen and Wu, Hexing and Weng, Xiaoyang and Zheng, Yuxin and Ming, Yuhang and Kong, Wanzeng},
  title = {Multi-Modal Synergistic Implicit Image Enhancement for Efficient Optical Flow Estimation},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = jun,
  year = {2025},
  pages = {2173-2182},
}

SIViP

Bidirectional joint estimation of optical flow and scene flow with Gaussian-guided attention

Weichen Dai, Xiaoyang Weng, Donglei Sun, Yuhang Ming, and 1 more author

Signal, Image and Video Processing, Jun 2025

Bib

@article{Dai0025sivip,
  author = {Dai, Weichen and Weng, Xiaoyang and Sun, Donglei and Ming, Yuhang and Kong, Wanzeng},
  title = {Bidirectional joint estimation of optical flow and scene flow with Gaussian-guided attention},
  journal = {Signal, Image and Video Processing},
  volume = {19},
  year = {2025},
  number = {6},
  url = {https://doi.org/10.1007/s11760-025-04042-6},
  issn = {1863-1711},
  doi = {10.1007/s11760-025-04042-6},
}

SP-L

Independent Components Time-Frequency Purification With Channel Consensus Against Adversarial Attack in SSVEP-Based BCIs

Hangjie Yi, Jingsheng Qian, Yuhang Ming, and Wanzeng Kong

IEEE Signal Processing Letters, Jun 2025

Bib

@article{Yi2025tfpurification,
  author = {Yi, Hangjie and Qian, Jingsheng and Ming, Yuhang and Kong, Wanzeng},
  journal = {IEEE Signal Processing Letters},
  title = {Independent Components Time-Frequency Purification With Channel Consensus Against Adversarial Attack in SSVEP-Based BCIs},
  year = {2025},
  volume = {32},
  number = {},
  pages = {116-120},
  keywords = {Perturbation methods;Electroencephalography;Brain modeling;Time-frequency analysis;Purification;Signal processing algorithms;Transforms;Correlation;Computational modeling;Benchmark testing;Adversarial attack;electroencephalogram;purification;steady state visual evoked potential (SSVEP)},
  doi = {10.1109/LSP.2024.3501274},
}

EEG-DGRN: dynamic graph representation network for subject-independent ERP detection

Jiabin Zhu, Xuanyu Jin, Yuhang Ming, and Wanzeng Kong

Brain-Apparatus Communication: A Journal of Bacomics , Jan 2025

Bib

@article{Zhu2025EEGDGRN,
  author = {Zhu, Jiabin and Jin, Xuanyu and Ming, Yuhang and Kong, Wanzeng},
  title = {EEG-DGRN: dynamic graph representation network for subject-independent ERP detection},
  journal = {Brain-Apparatus Communication: A Journal of Bacomics },
  year = {2025},
  month = jan,
  day = {08},
  volume = {4},
  number = {1},
  pages = {},
  doi = {10.1080/27706710.2024.2447576},
  url = {https://doi.org/10.1080/27706710.2024.2447576},
}

2024

AEGIS-Net: Attention-guided Multi-Level Feature Aggregation for Indoor Place Recognition

Yuhang Ming, Jian Ma, Xingrui Yang, Weichen Dai, and 2 more authors

In 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jan 2024

arXiv Bib Code

@inproceedings{Ming2024aegisnet,
  author = {Ming, Yuhang and Ma, Jian and Yang, Xingrui and Dai, Weichen and Peng, Yong and Kong, Wanzeng},
  booktitle = {2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {AEGIS-Net: Attention-guided Multi-Level Feature Aggregation for Indoor Place Recognition},
  year = {2024},
}

ICME

Time-Frequency Jointed Imperceptible Adversarial Attack to Brainprint Recognition with Deep Learning Models

Hangjie Yi, Yuhang Ming, Dongjun Liu, and Wanzeng Kong

In 2024 IEEE International Conference on Multimedia and Expo (ICME), Jan 2024

Bib

@inproceedings{Yi2024tfattack,
  author = {Yi, Hangjie and Ming, Yuhang and Liu, Dongjun and Kong, Wanzeng},
  booktitle = {2024 IEEE International Conference on Multimedia and Expo (ICME)},
  title = {Time-Frequency Jointed Imperceptible Adversarial Attack to Brainprint Recognition with Deep Learning Models},
  year = {2024},
  volume = {},
  number = {},
  pages = {1-6},
  keywords = {Deep learning;Wavelet transforms;Time-frequency analysis;Wavelet domain;Target recognition;Biological system modeling;Visual systems;Brain modeling;Electroencephalography;Time-domain analysis;EEG;brainprint;adversarial attack;biometrics;wavelets transform},
  doi = {10.1109/ICME57554.2024.10688012},
}

2023

Book Chapter

In-Sensor Visual Devices for Perception and Inference

Yanan Liu, Hepeng Ni, Chao Yuwen, Xinyu Yang, and 4 more authors

Jan 2023

Bib PDF

@inbook{Liu2023,
  author = {Liu, Yanan and Ni, Hepeng and Yuwen, Chao and Yang, Xinyu and Ming, Yuhang and Zhong, Huixin and Lu, Yao and Ran, Liang},
  title = {In-Sensor Visual Devices for Perception and Inference},
  booktitle = {Autonomous Driving Perception: Fundamentals and Applications},
  year = {2023},
  publisher = {Springer Nature Singapore},
  address = {Singapore},
  pages = {1--35},
  isbn = {978-981-99-4287-9},
  doi = {10.1007/978-981-99-4287-9_1},
  url = {https://doi.org/10.1007/978-981-99-4287-9_1},
}

IROS

EDI: ESKF-based Disjoint Initialization for Visual-Inertial SLAM

Weihan Wang, Jiani Li, Yuhang Ming, and Philippos Mordohai

In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Jan 2023

arXiv Bib

@inproceedings{Wang2023edi,
  author = {Wang, Weihan and Li, Jiani and Ming, Yuhang and Mordohai, Philippos},
  booktitle = {2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  title = {EDI: ESKF-based Disjoint Initialization for Visual-Inertial SLAM},
  year = {2023},
}

CVPR

PVO: Panoptic visual odometry

Weicai Ye, Xinyue Lan, Shuo Chen, Yuhang Ming, and 4 more authors

In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jan 2023

arXiv Bib Website

@inproceedings{Ye2023pvo,
  title = {PVO: Panoptic visual odometry},
  author = {Ye, Weicai and Lan, Xinyue and Chen, Shuo and Ming, Yuhang and Yu, Xingyuan and Bao, Hujun and Cui, Zhaopeng and Zhang, Guofeng},
  booktitle = {2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  pages = {9579-9589},
}

Thesis

Enhancing RGB-D SLAM with Deep Learning

Yuhang Ming

Jan 2023

Bib PDF

2022

iDF-SLAM: End-to-End RGB-D SLAM with Neural Implicit Mapping and Deep Feature Tracking

Yuhang Ming, Weicai Ye, and Andrew Calway

arXiv preprint arXiv:2209.07919, Jan 2022

arXiv Bib

@article{Ming2022idfslam,
  title = {iDF-SLAM: End-to-End RGB-D SLAM with Neural Implicit Mapping and Deep Feature Tracking},
  author = {Ming, Yuhang and Ye, Weicai and Calway, Andrew},
  journal = {arXiv preprint arXiv:2209.07919},
  year = {2022},
}

CGiS-Net: Aggregating Colour, Geometry and Implicit Semantic Features for Indoor Place Recognition

Yuhang Ming, Xingrui Yang, Guofeng Zhang, and Andrew Calway

In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Jan 2022

arXiv Bib Code

@inproceedings{Ming2022cgisnet,
  author = {Ming, Yuhang and Yang, Xingrui and Zhang, Guofeng and Calway, Andrew},
  booktitle = {2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  title = {CGiS-Net: Aggregating Colour, Geometry and Implicit Semantic Features for Indoor Place Recognition},
  year = {2022},
  pages = {6991-6997},
  doi = {10.1109/IROS47612.2022.9981113},
}

ISMAR

Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation

Xingrui Yang, Hai Li, Hongjia Zhai, Yuhang Ming, and 2 more authors

In 2022 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), Jan 2022

arXiv Bib Code Website

@inproceedings{Yang2022voxfusion,
  author = {Yang, Xingrui and Li, Hai and Zhai, Hongjia and Ming, Yuhang and Liu, Yuqian and Zhang, Guofeng},
  booktitle = {2022 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)},
  title = {Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation},
  year = {2022},
  pages = {499-507},
  doi = {10.1109/ISMAR55827.2022.00066},
}

FD-SLAM: 3-D Reconstruction Using Features and Dense Matching

Xingrui Yang, Yuhang Ming, Zhaopeng Cui, and Andrew Calway

In 2022 International Conference on Robotics and Automation (ICRA), Jan 2022

arXiv Bib

@inproceedings{Yang2022fdslam,
  author = {Yang, Xingrui and Ming, Yuhang and Cui, Zhaopeng and Calway, Andrew},
  booktitle = {2022 International Conference on Robotics and Automation (ICRA)},
  title = {FD-SLAM: 3-D Reconstruction Using Features and Dense Matching},
  year = {2022},
  pages = {8040-8046},
  doi = {10.1109/ICRA46639.2022.9812049},
}

2021

Object-Augmented RGB-D SLAM for Wide-Disparity Relocalisation

Yuhang Ming, Xingrui Yang, and Andrew Calway

In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Jan 2021

arXiv Bib Code

@inproceedings{Ming2021objreloc,
  author = {Ming, Yuhang and Yang, Xingrui and Calway, Andrew},
  booktitle = {2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  title = {Object-Augmented RGB-D SLAM for Wide-Disparity Relocalisation},
  year = {2021},
  pages = {2203-2209},
  doi = {10.1109/IROS51168.2021.9636034},
}

2020

CVPR Chanllenge

Discriminative representation loss (DRL) for continual learning: A solution for CLVision challenge

Yu Chen, Jian Ma, HanYuan Wan, Yuhang Ming, and 2 more authors

In CVPR 2020 CLVision challenge, Jan 2020

Bib PDF

@inproceedings{Chen2020drl,
  author = {Chen, Yu and Ma, Jian and Wan, HanYuan and Ming, Yuhang and Massiah, Jordan and Diethe, Tom},
  title = {Discriminative representation loss (DRL) for continual learning: A solution for CLVision challenge},
  year = {2020},
  url = {https://www.amazon.science/publications/discriminative-representation-loss-drl-for-continual-learning-a-solution-for-clvision-challenge},
  booktitle = {CVPR 2020 CLVision challenge},
}