Dr Tobias Fischer
Faculty of Engineering,
School of Electrical Engineering & Robotics
Biography
Research OverviewDr Tobias Fischer conducts interdisciplinary research at the intersection of computer vision, cognitive robotics and computational cognition. His research goal is to provide robots with perceptional abilities that allow interactions with humans in a human-like manner. To develop these perceptional abilities, Tobias believes that it is useful to study the principles used by the animal visual system. He uses these principles to develop new computer vision algorithms and validates their effectiveness in intelligent robotic systems.
Research Experience
Dr Fischer is the Principal Investigator of a grant entitled "Spike-based Visual Place Recognition using Intel's Loihi" funded by the Intel Neuromorphic Computing Lab. He is further co-investigator of an Amazon Research Award on "Complementarity-Aware Multi-Process Fusion for Long Term Localization". Dr Fischer was a co-author and named lead researcher of two applications for the Samsung Global Research Outreach program, which resulted in 200,000 USD commercial funding. In addition, he has been working on major research projects funded by European Union FP7 and H2020 programs, and the Multidisciplinary University Research Initiative (MURI). His papers have received two best poster awards:
- Samsung AI Forum 2018 for the paper entitled "Context-aware Deep Feature Compression for High-speed Visual Tracking" (appeared at CVPR2018)
- IEEE International Conference on Computer Vision 2019 Workshop on Gaze Estimation and Prediction in the Wild for the paper entitled "RT-BENE: A Dataset and Baselines for Real-Time Blink Estimation in Natural Environments"
Before joining QUT as a Research Fellow in January 2020, Dr Fischer was a postdoctoral researcher in the Personal Robotics Lab at Imperial College London. He received a PhD from Imperial College with the thesis topic: "Perspective Taking in Robots: A Framework and Computational Model" in January 2019. The thesis has been awarded the Queen Mary UK Best Thesis in Robotics Award 2018 and the Eryl Cadwaladr Davies Prize for the best thesis in the Electrical and Electronic Engineering Department at Imperial College 2018. Since September 2020, Tobias is a professionally registered Chartered Engineer. Dr Fischer received the M.Sc. degree in Artificial Intelligence from The University of Edinburgh, in August 2014, and a B.Sc. degree in Computer Engineering from Ilmenau University of Technology, Germany, in 2013. He wrote his Bachelor thesis in John Tsotsos' Lab for Active and Attentive Vision, at the York University, Canada. From February 2012 until August 2014, he was a scholarship holder at the prestigious German National Academic Foundation (Studienstiftung des Deutschen Volkes).
Web Links
Publication highlights
- Hausler, Garg, Xu, Milford & Fischer: Patch-NetVLAD: Multi-Scale Fusion of Locally Global Descriptors for Place Recognition (IEEE Conference on Computer Vision and Pattern Recognition 2021)
- Fischer & Milford: Event-Based Visual Place Recognition With Ensembles of Temporal Windows (IEEE Robotics and Automation Letters 2020)
- Fischer & Demiris: Computational Modelling of Embodied Visual Perspective-taking (IEEE Transactions on Cognitive and Developmental Systems)
- Fischer, Chang & Demiris: RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments (European Conference on Computer Vision ECCV2018)
- Choi et al.: Context-aware Deep Feature Compression for High-speed Visual Tracking (IEEE Conference on Computer Vision and Pattern Recognition CVPR2018)
- Chang, Fischer, Petit, Zambelli and Demiris: Learning Kinematic Structure Correspondences Using Multi-Order Similarities (IEEE Transactions on Pattern Analysis and Machine Learning TPAMI2018 & CVPR2016)
Personal details
Positions
- Senior Lecturer
Faculty of Engineering,
School of Electrical Engineering & Robotics
Keywords
Robotics, Computer Vision, Computational Cognition, Place Recognition, Gaze Estimation, Event Cameras, Spiking Neural Networks
Research field
Artificial intelligence, Electrical engineering
Field of Research code, Australian and New Zealand Standard Research Classification (ANZSRC), 2020
Qualifications
- Doctor of Philosophy (Imperial College, London)
- M.Sc. (University of Edinburgh)
- B.Sc. (Other)
Professional memberships and associations
- Fellow, Higher Education Academy (FHEA)
- Chartered Engineer (CEng)
- Senior Member, Institute of Electrical and Electronics Engineers (SMIEEE)
- Member, Institution of Engineering and Technology (MIET)
- Member, British Machine Vision Association (BMVA)
- Member, IEEE Robotics and Automation Society
Teaching
Dr Fischer's teaching profile accounts for over 85 hours of teaching in a wide range of undergraduate and postgraduate courses. He also regularly supervises PhD, MSc/MEng and BSc/BEng students, and mentors lab members on an ongoing basis to support their success. Dr Fischer is a Fellow of the Higher Education Academy which demonstrates his overall commitment to professionalism in learning and teaching.
Teaching Overview:
- Assessor, EGH400-1, Winter 2021 (QUT)
- Assessor, EGH408, Spring 2020 (QUT)
- Guest Lecturer, EGH444, Spring 2020 (QUT)
- Guest Lecturer, Human-Centered Robotics, Autumn 2019 (Imperial College London)
- Assessor, Mobile Healthcare and Machine Learning, Spring 2019 (Imperial College London)
- Assessor, Human-Centered Robotics, Autumn 2018 (Imperial College London)
- Tutor, Object-Oriented Programming, Spring 2014 (University of Edinburgh)
- Tutor, Processing Formal and Natural Languages, Autumn 2013 (University of Edinburgh)
- Tutor, Software Engineering, Autumn 2013 (University of Edinburgh)
- Tutor, Algorithms and Programming, Autumn 2011 (Ilmenau University of Technology)
- Tutor, Algorithms and Programming, Autumn 2010 (Ilmenau University of Technology)
Supervision Overview:
- PhD student: "Global relocalization across changing conditions for metric, keyframe-based visual SLAM systems", Queensland University of Technology, 2021 - 2022 (RAL paper)
- PhD student: "Sensor-Based Positioning and Guidance at the Edge", Queensland University of Technology, 2021 - now
- BEng student: "Feature Extraction for Event-based Place Recognition", 2021
- BEng student: "Long-Duration Autonomous Exploration in GPS-Denied Environments", 2020-2021
- PhD student: "Re-Evolving Biological Neural Networks for Spatially-informed Intelligence", Queensland University of Technology, 2021 - 2024
- PhD student: "Vision-based localisation during transitions between environments", Queensland University of Technology, 2021 - 2024
- PhD student: "Appearance and Viewpoint Invariant Visual Place Recognition using Multi-scale and Multi-modality Systems" (CVPR2021 proceedings paper), Queensland University of Technology, 2020 - 2021
- PhD student: "Real-Time Multi-Person Pose Tracking using Data Assimilation" (WACV2020 proceedings paper), Imperial College London, 2017 - 2019
- Research assistant on the PAL H2020 project: "Real-Time Knowledge-ability Prediction on Mobile Devices", Imperial College London, 2018 - 2019
- BEng in Electrical and Electronic Engineering: "Use of Gaze Estimation in Mobile Learning Environments to Infer Text Comprehension", Imperial College London, 2019
- MEng in Informatics and Systems Modeling: "Fusing Linguistic and Gaze Information for Human Robot Interaction" (ICCV2019 workshop proceedings paper best poster award), Imperial College London, 2018
- MEng in Electrical and Electronic Engineering: "Comper: A Collaborative Musical Accompaniment System using Deep Latent Vector Models", Imperial College London, 2018
- MSc in Computing: "Towards Verbal Control of Humanoid Robots", Imperial College London, 2018
Publications
Research outputs by year
- Hausler, S., Garg, S., Xu, M., Milford, M. & Fischer, T. (2021). Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14136–14147. https://eprints.qut.edu.au/213030
- Fischer, T., Chang, H. & Demiris, Y. (2018). RT-GENE: Real-time eye gaze estimation in natural environments. Computer Vision - ECCV 2018: 15th European Conference, Proceedings, Part X, 339–357.
- Fischer, T. & Demiris, Y. (2020). Computational modeling of embodied visual perspective taking. IEEE Transactions on Cognitive and Developmental Systems, 12(4), 723–732. https://eprints.qut.edu.au/197700
- Fischer, T., Vollprecht, W., Traversaro, S., Yen, S., Herrero, C. & Milford, M. (2022). A RoboStack Tutorial: Using the Robot Operating System Alongside the Conda and Jupyter Data Science Ecosystems. IEEE Robotics and Automation Magazine, 29(2), 65–74. https://eprints.qut.edu.au/228392
- Garg, S., Fischer, T. & Milford, M. (2021). Where Is Your Place, Visual Place Recognition? Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21), 4416–4425. https://eprints.qut.edu.au/212869
- Fischer, T. & Milford, M. (2020). Event-Based Visual Place Recognition With Ensembles of Temporal Windows. IEEE Robotics and Automation Letters, 5(4), 6924–6931. https://eprints.qut.edu.au/205321
- Hussaini, S., Milford, M. & Fischer, T. (2022). Spiking Neural Networks for Visual Place Recognition Via Weighted Neuronal Assignments. IEEE Robotics and Automation Letters, 7(2), 4094–4101. https://eprints.qut.edu.au/228964
- Fischer, T. & Milford, M. (2022). How Many Events Do You Need? Event-Based Visual Place Recognition Using Sparse But Varying Pixels. IEEE Robotics and Automation Letters, 7(4), 12275–12282. https://eprints.qut.edu.au/236180
- Chang, H., Fischer, T., Petit, M., Zambelli, M. & Demiris, Y. (2018). Learning kinematic structure correspondences using multi-order similarities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(12), 2920–2934.
- Fischer, T. & Demiris, Y. (2016). Markerless perspective taking for humanoid robots in unconstrained environments. Proceedings of the 2016 IEEE International Conference on Robotics and Automation (ICRA), 3309–3316.
QUT ePrints
For more publications by Tobias, explore their research in QUT ePrints (our digital repository).
Awards
- Type
- Academic Honours, Prestigious Awards or Prizes
- Reference year
- 2023
- Details
- My first author paper "Computational Modeling of Embodied Visual Perspective Taking" has received the 2023 IEEE Transactions on Cognitive & Developmental Systems Outstanding Paper Award.
- Type
- Academic Honours, Prestigious Awards or Prizes
- Reference year
- 2021
- Details
- I am the senior author of the winning contribution (Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition; CVPR2021) at the ECCV 2020 Workshop on Long-Term Visual Localization under Changing Conditions.
- Type
- Academic Honours, Prestigious Awards or Prizes
- Reference year
- 2019
- Details
- Our Cortacero, Fischer and Demiris 2019 paper (RT-BENE: a dataset and baselines for real-time blink estimation in natural environments) won the best poster award at the ICCV Gaze Estimation and Prediction in the Wild workshop.
- Type
- Fellowships
- Reference year
- 2019
- Details
- I am a Fellow of the Higher Education Academy
- Type
- Academic Honours, Prestigious Awards or Prizes
- Reference year
- 2018
- Details
- My thesis has been recognised with the Eryl Cadwaladr Davies prize for the best thesis 2017-2018 in the Electrical and Electronic Engineering Department at Imperial College London.
- Type
- Academic Honours, Prestigious Awards or Prizes
- Reference year
- 2018
- Details
- I have been awarded the renowned Queen Mary UK Best PhD in Robotics Award 2018. The competition is open to all PhD students in the field of robotics within the UK.
- Type
- Fellowships
- Reference year
- 2012
- Details
- I have been awarded a scholarship by the German National Merit Foundation (Studienstiftung des Deutschen Volkes), Germany's largest, oldest and most prestigious scholarship organisation. The scholarship included tuition fees, travel grants and a living allowance. The foundation supports less than 0.5% of German students.
Supervision
Looking for a postgraduate research supervisor?
I am currently accepting research students for Honours, Masters and PhD study.
- Implicit representations for place recognition and robot localisation
- Adaptive and efficient robot positioning
You can browse existing student topics offered by QUT or propose your own topic.
Current supervisions
- Robust Visual Place Recognition and 3D Scene Reconstruction Using Events and Frames
PhD, Associate Supervisor
Other supervisors: Professor Michael Milford - Bio-inspired Neural Networks for Visual Place Recognition
PhD, Principal Supervisor
Other supervisors: Professor Michael Milford - Bio-inspired SLAM using Continuous Attractor Networks
PhD, Associate Supervisor
Other supervisors: Professor Michael Milford - Learning Local and Global Place Representations for Visual Place Recognition
PhD, Associate Supervisor
Other supervisors: Professor Michael Milford - Autonomous 3D Neural Scene Reconstruction
PhD, Associate Supervisor
Other supervisors: Professor Niko Suenderhauf, Professor Michael Milford - Data Pre-Processing for Visual Localization Tasks
PhD, Principal Supervisor
Other supervisors: Professor Michael Milford, Dr Alejandro Fontan Villacampa - Weakly supervised segmentation of underwater imagery
PhD, Principal Supervisor
Other supervisors: Dr Ross Marchant, Dr Frederic Maire, Professor Niko Suenderhauf