Kirill Sidorov

Kirill Sidorov

Lecturer

Cardiff University

Biography

Dr Kirill Sidorov is a lecturer in the School of Computer Science and Informatics and a member of the Visual Computing research section. His research interests span a wide range of interdisciplinary areas, especially applications of machine learning and computer vision to robotics, medicine, psychology, archaeology, crime prevention, and computational music. Dr Kirill Sidorov is also a Deputy Director of Postgraduate Research. He is a faculty advisor for the Cardiff Autonomous Racing team. Kirill is an experienced musician, with interest in composition and musicology, and a keen chess enthusiast.

Interests
  • Computer Vision
  • Machine Learning
  • Music
  • Robotics
Education
  • PhD in Computer Science, 2011

    Cardiff university

  • BEng in Computer Systems Engineering, 2006

    Cardiff university

PhD Alumni

(2021). An Investigation into Explanations for Convolutional Neural Networks. PhD Thesis, Cardiff University.

PDF

(2021). Poisson-Binomial Counting for Learning Prediction Sparsity. PhD Thesis, Cardiff University.

PDF

(2018). Automated Screening Methods for Mental and Neuro-developmental Disorders. PhD Thesis, Cardiff University.

PDF

Publications

(2021). SWAG-V: Explanations for Video Using Superpixels Weighted by Average Gradients. In WACV 2022.

PDF Cite DOI

(2021). An Investigation of Music Analysis by the Application of Grammar-based Compressors. In Journal of New Music Research.

PDF Cite DOI

(2021). Learning Precise Temporal Point Event Detection with Misaligned Labels. In AAAI 2021.

PDF Cite Code Conference

(2020). SWAG: Superpixels Weighted by Average Gradients for Explanations of CNNs. In WACV 2021.

Cite DOI

(2020). Association of Violence with Urban Points of Interest. In PLoS ONE.

PDF Cite DOI

(2020). Learning Multi-instance Sub-pixel Point Localization. In ACCV 2020.

PDF Cite Code Supplemental

(2020). Robust Temporal Point Event Localization through Smoothing and Counting. In ICML Workshop on Uncertainty & Robustness in Deep Learning.

PDF

(2019). Weakly-supervised Temporal Localization via Occurrence Count Learning. In ICML 2019.

PDF Cite Code Supplementary

(2018). Computational Paralinguistics: Automatic Assessment of Emotions, Mood and Behavioural State from Acoustics of Speech. In Interspeech 2018.

PDF Cite DOI

(2017). An Open-data, Agent-based Model of Alcohol Related Crime. In IEEE AVSS 2017.

Cite DOI

(2017). Depression Severity Prediction Based on Biomarkers of Psychomotor Retardation. In AVEC 2017.

PDF Cite

(2017). Estimating the Age of Birch Bark Manuscripts using Computational Paleography. In Programming and Computer Software.

Journal

(2017). Paleographic Dating of Birch Bark Manuscripts. In GraphiCon 2017.

PDF Cite

(2016). A Smallest Grammar Approach to the Symbolic Analysis of Music. In Trends in Music Information Seeking, Behavior, and Retrieval for Creativity.

PDF Cite

(2015). Assistive Sports Video Annotation: Modelling and Detecting Complex Events in Sports Video. In MathSport International 2015.

PDF DOI

(2014). Music Analysis as a Shortest Grammar Problem. In ISMIR 2014.

PDF Cite

(2014). Learnt Real-time Meshless Simulation. In Computer Graphics Forum.

Cite DOI

(2014). μTunes: A Study of Musicality Perception in an Evolutionary Context. In ICMC 2014.

PDF Cite

(2013). Harmonic Parameterization by Electrostatics. In ACM Transactions on Graphics.

PDF DOI

(2012). Detailing Patient Specific Modeling to Aid Clinical Decision-Making. In Patient-Specific Computational Modeling.

PDF Cite DOI

(2011). Efficient Groupwise Non-rigid Registration of Textured Surfaces. In CVPR 2011.

PDF Cite DOI

(2009). An Efficient Stochastic Approach to Groupwise Non-rigid Image Registration. In CVPR 2009.

PDF Cite DOI

(2007). Towards Efficient 3D Facial Appearance Models. In ACM SIGGRAPH Symposium on Computer Animation.

PDF Cite

(2006). Discovering Realistic Facial Dynamics for Animation. In CVMP 2006.

PDF Cite DOI

(2006). Real-time Multi-camera 3D Tracking System. In CVMP 2006.

PDF Cite DOI

Contact