TAS Publications

@inproceedings{10.1145/3568162.3576969,

title = {Resolving Conflicts During Human-Robot Co-Manipulation},

author = {Zaid Al-Saadi and Yahya M. Hamad and Yusuf Aydin and Ayse Kucukyilmaz and Cagatay Basdogan},

url = {https://doi.org/10.1145/3568162.3576969},

doi = {10.1145/3568162.3576969},

isbn = {9781450399647},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the 2023 ACM/IEEE International Conference on Human-Robot Interaction},

pages = {243–251},

publisher = {Association for Computing Machinery},

address = {Stockholm, Sweden},

series = {HRI '23},

keywords = {conflict resolution, dyadic manipulation, haptic features, Machine learning, physical human-robot interaction},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{7b1683ac2bbf4dfba61d9305dd53c05c,

title = {Revisiting Deep Fisher Vectors: Using Fisher Information to Improve Object Classification},

author = {Sarah Ahmed and Tayyaba Azim and Joseph Early and Sarvapali Ramchurn},

url = {https://bmvc2022.org/},

year  = {2022},

date = {2022-10-01},

booktitle = {British Machine Vision Conference},

abstract = {Although deep learning models have become the gold standard in achieving outstanding results on a large variety of computer vision and machine learning tasks, the use of kernel methods has still not gone out of trend because of its potential to beat deep learning performances at a number of occasions. Given the potential of kernel techniques, prior works have also proposed the use of hybrid approaches combining deep learning with kernel learning to complement their respective strengths and weaknesses. This work develops this idea further by introducing an improved version of Fisher kernels derived from the deep Boltzmann machines (DBM). Our improved deep Fisher kernel (IDFK) utilises an approximation of the Fisher information matrix to derive improved Fisher vectors. We show IDFK can be utilised to retain a high degree of class separability, making it appropriate for classification and retrieval tasks. The efficacy of the proposed approach is evaluated on three benchmark data sets: MNIST, USPS and Alphanumeric, showing an improvement in classification performance over existing kernel approaches, and comparable performance to deep learning methods, but with much reduced computational costs. Using explainable AI methods, we also demonstrate why our IDFK leads to better classification performance.},

note = {British Machine Vision Conference, BMVC 2022 ; Conference date: 21-11-2022 Through 24-11-2022},

keywords = {Machine learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1007/978-3-031-17899-3_2,

title = {A Study of Demographic Bias in CNN-Based Brain MR Segmentation},

author = {Stefanos Ioannou and Hana Chockler and Alexander Hammers and Andrew P. King},

editor = {Ahmed Abdulkadir and Deepti R. Bathula and Nicha C. Dvornek and Mohamad Habes and Seyed Mostafa Kia and Vinod Kumar and Thomas Wolfers},

year  = {2022},

date = {2022-01-01},

booktitle = {Machine Learning in Clinical Neuroimaging},

pages = {13--22},

publisher = {Springer Nature Switzerland},

keywords = {Machine learning, Neuroimaging},

pubstate = {published},

tppubtype = {inproceedings}

}