- 319
- 441 025
Andreas Maier
Germany
Registrace 31. 10. 2012
Prof. Dr. Andreas Maier studied Computer Science, graduated in 2005, and received his Ph.D. in 2009. From 2005 to 2009 he developed the first online speech intelligibility assessment tool - PEAKS - that has been used to analyze over 4.000 patients and control subjects so far. From 2009 to 2010, he started working on flat-panel C-arm CT as a post-doctoral fellow at the Radiological Sciences Laboratory in the Department of Radiology at Stanford University. From 2011 to 2012 he joined Siemens Healthcare as an innovation project manager and was responsible for reconstruction topics in the Angiography and X-ray business unit. In 2015 he became a professor and head of the Pattern Recognition Lab. Since 2016, he is a member of the steering committee of the European Time Machine Consortium. In 2018, he was awarded an ERC Synergy Grant “4D nanoscope”. Current research interests focus on medical imaging, image and audio processing, digital humanities, and interpretable machine learning.
Beyond the Patterns 50 - Jonghyun Choi - Continual Learning in Practical Scenarios
We have the great honor to welcome Jonghyun Choi to our lab for an invited presentation!
Abstract: Continual learning, especially class-incremental learning uses an episodic memory for past knowledge for better performance. Updating a model with the episodic memory is similar to (1) updating a model with past knowledge in the memory by a few-shot learning scheme, and (2) learning an imbalanced distribution of past data and the present data. We address the unrealistic factors in popular continual learning setups and propose a few ideas to make the continual learning research in realistic scenarios.
Short Bio: Jonghyun received the B.S. and M.S. degrees in electrical engineering and computer science from Seoul National University, Seoul, South Korea in 2003 and 2008, respectively. He received a Ph.D. degree from University of Maryland, College Park in 2015, under the supervision of Prof. Larry S. Davis. He is currently an associate professor at Yonsei University, Seoul, South Korea. During his PhD, he has worked as a research intern in US Army Research Lab (2012), Adobe Research (2013), Disney Research Pittsburgh (2014) and Microsoft Research Redmond (2014). He was a senior researcher at Comcast Applied AI Research, Washington, DC from 2015 to 2016. He was a research scientist at Allen Institute for Artificial Intelligence (AI2), Seattle, WA from 2016 to 2018 and is currently an affiliated research scientist. He was an assistant professor at GIST, South Korea. His research interest includes visual recognition using weakly supervised data for semantic understanding of images and videos and visual understanding for edge devices and household robots.
References
ppolon.github.io
Register for more upcoming talks here: lme.tf.fau.de/research/beyond-the-patterns/
This video is released under CC BY 4.0. Please feel free to share and reuse. See "Beyond the Patterns" without ads here: www.fau.tv/course/id/1868
For reminders to watch the new video follow on Twitter maier_ak or LinkedIn www.linkedin.com/in/andreas-maier-a6870b1a6/. Also, join our network for information about talks, videos, and job offers in our Facebook and LinkedIn Groups lme.tf.fau.de/lab/join-the-pattern-recognition-lab/.
Music Reference:
Damiano Baldoni - Thinking of You (Intro)
freemusicarchive.org/music/Damiano_Baldoni/Old_Beat/Thinking_of_you_1513
Damiano Baldoni - Poenia (Outro)
freemusicarchive.org/music/Damiano_Baldoni/Crystal_Lake/Poenia
Abstract: Continual learning, especially class-incremental learning uses an episodic memory for past knowledge for better performance. Updating a model with the episodic memory is similar to (1) updating a model with past knowledge in the memory by a few-shot learning scheme, and (2) learning an imbalanced distribution of past data and the present data. We address the unrealistic factors in popular continual learning setups and propose a few ideas to make the continual learning research in realistic scenarios.
Short Bio: Jonghyun received the B.S. and M.S. degrees in electrical engineering and computer science from Seoul National University, Seoul, South Korea in 2003 and 2008, respectively. He received a Ph.D. degree from University of Maryland, College Park in 2015, under the supervision of Prof. Larry S. Davis. He is currently an associate professor at Yonsei University, Seoul, South Korea. During his PhD, he has worked as a research intern in US Army Research Lab (2012), Adobe Research (2013), Disney Research Pittsburgh (2014) and Microsoft Research Redmond (2014). He was a senior researcher at Comcast Applied AI Research, Washington, DC from 2015 to 2016. He was a research scientist at Allen Institute for Artificial Intelligence (AI2), Seattle, WA from 2016 to 2018 and is currently an affiliated research scientist. He was an assistant professor at GIST, South Korea. His research interest includes visual recognition using weakly supervised data for semantic understanding of images and videos and visual understanding for edge devices and household robots.
References
ppolon.github.io
Register for more upcoming talks here: lme.tf.fau.de/research/beyond-the-patterns/
This video is released under CC BY 4.0. Please feel free to share and reuse. See "Beyond the Patterns" without ads here: www.fau.tv/course/id/1868
For reminders to watch the new video follow on Twitter maier_ak or LinkedIn www.linkedin.com/in/andreas-maier-a6870b1a6/. Also, join our network for information about talks, videos, and job offers in our Facebook and LinkedIn Groups lme.tf.fau.de/lab/join-the-pattern-recognition-lab/.
Music Reference:
Damiano Baldoni - Thinking of You (Intro)
freemusicarchive.org/music/Damiano_Baldoni/Old_Beat/Thinking_of_you_1513
Damiano Baldoni - Poenia (Outro)
freemusicarchive.org/music/Damiano_Baldoni/Crystal_Lake/Poenia
zhlédnutí: 277
Video
Beyond the Patterns 49 - Farah Deeba - Multimodal Imaging of the Placenta
zhlédnutí 370Před rokem
We have the great honor to welcome Farah Deeba to our lab for an invited presentation! Abstract: Maternal mortality rates worldwide are unacceptably high. Early detection and timely management of pregnancy complications could prevent most of these deaths. Unfortunately, current ultrasound-based pregnancy screening tools are dependent on system settings and user interpretation (contributing to i...
Beyond the Patterns 48 - Robert Sablatnig (TU Vienna): Multispectral Imaging & Writer Identification
zhlédnutí 167Před rokem
We have the great honor to welcome Robert Sablatnig to our lab for an invited presentation! Abstract:The Computer Vision Lab @ TU Wien is working on cultural heritage related fields for more than 20 years. This presentation gives an insight on the latest achievements in the area of multispectral imaging as a prerequisite for analyzing historic manuscripts and on Automatic Writer Identification ...
How to "Hack" Proprietary AI Image Processing Software
zhlédnutí 3,9KPřed 2 lety
In the domain of medical image processing, medical device manufacturers protect their intellectual property in many cases by shipping only compiled software, i.e. binary code which can be executed but is difficult to be understood by a potential attacker. In this paper, we investigate how well this procedure is able to protect image processing algorithms. In particular, we investigate whether t...
Beyond the Patterns 47 - Heidi Christiansen (Sheffield): Automated Processing of Pathological Speech
zhlédnutí 605Před 2 lety
We have the great honor to welcome Heidi Christianseni to our lab for an invited presentation! Abstract: This talk will outline the major challenging in porting mainstream speech technology to the domain of clinical applications; in particular, the need for personalised systems, the challenge of working in an inherently sparse data domain and developing meaningful collaborations with all stakeh...
Beyond the Patterns 46 - Mirco Ravanelli (MILA): The Speech Brain Project
zhlédnutí 497Před 2 lety
We have the great honor to welcome Mirco Ravanelli to our lab for an invited presentation! Abstract: SpeechBrain is an open-source and all-in-one conversational AI toolkit. It is designed to facilitate the research and development of speech and language technologies by being simple, flexible, user-friendly, and well-documented. This talk describes the core architecture designed to support sever...
Beyond the Patterns 44 - Christian Baumgartner: The next decade in automated medical image analysis
zhlédnutí 480Před 2 lety
We have the great honor to welcome Christian Baumgartner to our lab for an invited presentation! Abstract: Adoption of machine learning in many fields is exceeding expert predictions and the technology is in many ways already shaping our daily lives. Machine learning certainly also has the potential to transform our health care system, however, so far clinical adoption has been hesitant. In my ...
Beyond the Patterns - Mert Sabuncu (Cornell U): Deep Learning for Compressed Imaging
zhlédnutí 776Před 2 lety
We have the great honor to welcome Mert Sabuncu to our lab for an invited presentation! Abstract: Imaging techniques such as MRI can be accelerated by sampling below the Shannon-Nyquist rate via compressed sensing. In this talk, I will consider the use of deep learning methods for this problem. First, I will present our approach for Learning-based Optimization of the Under-sampling PattErn, or ...
Beyond the Patterns 42 - Nils Köbis: Ethical Behavior by Humans and Machines
zhlédnutí 284Před 2 lety
We have the great honor to welcome Dr. Nils Köbis to our lab for an invited presentation! Abstract: Machines powered by Artificial Intelligence (AI) are now influencing the behavior of humans in ways that are both like and unlike the ways humans influence each other. In light of recent research showing that other humans can exert a strong corrupting influence on people’s ethical behavior, worry...
Beyond the Patterns 41 - David B. Lindell & Julien Martel: Implicit Neural Representation Networks
zhlédnutí 554Před 2 lety
It’s a great pleasure to welcome David B. Lindell and Julien Martel from Stanford Engineering to our Lab! Abstract: Implicitly defined, continuous, differentiable signal representations parameterized by neural networks have emerged as a powerful paradigm, offering many possible benefits over conventional representations and new capabilities in neural rendering and view synthesis. However, conve...
Interspeech 2021 - Conference Highlights - Day 4
zhlédnutí 187Před 2 lety
Summary of Day 4 on Interspeech 2021 Featured Talks & Papers: Keynote: Tomaš Mikolov: Language Modelling and Artificial Intelligence Survey: Alejandrina Crista: Child Language Acquisition studied with wearables Youxuan Ma: RW-Resnet: A Novel Speech Anti-Spoofing Model Using Raw Waveform Yue Chen: A Neural-Network-Based Approach to Identifying Speakers in Novels This video is released under CC B...
Interspeech 2021 - Conference Highlights - Day 3
zhlédnutí 307Před 2 lety
Summary of Day 3 on Interspeech 2021 Featured Talks & Papers: Keynote: Mounya Elhilali: Adaptive listening to everyday soundscapes Survey: Karen Livescu: Learning speech models from multi-modal data Ralf Schlueter: Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept Ekaterina Egorova: Out-of-Vocabulary Words Detection with Attention and CTC Alignments in an End-to-End AS...
Interspeech 2021 - Conference Highlights - Day 2
zhlédnutí 476Před 2 lety
Summary of Day 2 on Interspeech 2021 Featured Talks & Papers: Susumu Saito - VocalTurk: Exploring Feasibility of Crowdsourced Speaker Identification Min Xu - Effects of Aging and Age-Related Hearing Loss on Talker Discrimination Survey Talk: Sriram Ganapathy - Uncovering the acoustic cues of COVID-19 infection Keynote: Pascale Fung - Ethical and Technological Challenges of Conversational AI Amr...
Interspeech 2021 - Conference Highlights - Day 1
zhlédnutí 1,3KPřed 2 lety
This this a short video on the Highlights of Interspeech 2021 selected by Seung Her Yang and Andreas Maier. Selected Papers & Presentations: Heidy Christiansen: Towards automatic speech recognition for people with atypical speech Louis Ten Bosch: An Entropy-Based Approach in the DIANA Model of Human Word Comprehension Time-to-Event Models for Analysing Reaction Time Sequences Models of Reaction...
Beyond the Patterns 40 - Adrian Dalca - Unsupervised Learning of Image Correspondences
zhlédnutí 603Před 3 lety
I am very glad to announce Adrian Dalca as an invited speaker at our lab! Abstract: Image registration is fundamental to many tasks in image analysis. Classical image registration methods have undergone decades of technical development, but are often prohibitively slow since they solve an optimization problem for each 3D image pair. In this talk, I will introduce various models that leverage le...
Beyond the Patterns 39 - Jesse Jokerst - Photoacoustic Imaging in Medicine
zhlédnutí 288Před 3 lety
Beyond the Patterns 39 - Jesse Jokerst - Photoacoustic Imaging in Medicine
Beyond the Patterns 38 - Letterlocking: A Global Technology of Communication Security
zhlédnutí 120Před 3 lety
Beyond the Patterns 38 - Letterlocking: A Global Technology of Communication Security
Beyond the Patterns 36 - Gitta Kutyniok - Deep Neural Networks: The Mystery of Generalization
zhlédnutí 505Před 3 lety
Beyond the Patterns 36 - Gitta Kutyniok - Deep Neural Networks: The Mystery of Generalization
Beyond the Patterns 35 - Nils Thuerey - Differentiable Physics Simulations for Deep Learning
zhlédnutí 433Před 3 lety
Beyond the Patterns 35 - Nils Thuerey - Differentiable Physics Simulations for Deep Learning
Beyond the Patterns 34 - Amy Kuceyeski - Biological and Artificial Neural Networks
zhlédnutí 377Před 3 lety
Beyond the Patterns 34 - Amy Kuceyeski - Biological and Artificial Neural Networks
Maier Unleashed - Peer Review Rant - Part 2
zhlédnutí 1,6KPřed 3 lety
Maier Unleashed - Peer Review Rant - Part 2
Beyond the Patterns 33 - Tobias Reichenbach - Decoding the Neural Processing of Speech
zhlédnutí 282Před 3 lety
Beyond the Patterns 33 - Tobias Reichenbach - Decoding the Neural Processing of Speech
Maier Unleashed - Review Rant - Part 1
zhlédnutí 3,8KPřed 3 lety
Maier Unleashed - Review Rant - Part 1
Beyond the Patterns 32 - Raghavendra Selvan: Quantum Tensor Networks for Medical Image Analysis
zhlédnutí 557Před 3 lety
Beyond the Patterns 32 - Raghavendra Selvan: Quantum Tensor Networks for Medical Image Analysis
Medical Engineering - Optical Coherence Tomography
zhlédnutí 462Před 3 lety
Medical Engineering - Optical Coherence Tomography
Beyond the Patterns 31 - Roger Soberanis Uncertainty-based Graph Convolution Segmentation Refinement
zhlédnutí 133Před 3 lety
Beyond the Patterns 31 - Roger Soberanis Uncertainty-based Graph Convolution Segmentation Refinement
Medical Engineering - Emission Tomography
zhlédnutí 339Před 3 lety
Medical Engineering - Emission Tomography
Medical Engineering - Phase Contrast Imaging
zhlédnutí 2,5KPřed 3 lety
Medical Engineering - Phase Contrast Imaging
In MaxPooling indices the value changes while upsampling?
Dieser Mann ist besser als mein Professor, ich zieh mir immer diese Vorlesungen rein, falls ich das aus meiner Uni nicht verstehe!
😂😂😂
Hi, is there also a video playlist from the course introduction to pattern recognition? Cant find it in you channel or on your website.
Hello. In the journal Optics Letters, researchers Glen A. Sanders and Austin Taranta from Honeywell and the Optoelectronics Research Center at the University of Southampton in the UK describe how they used a new type of hollow-core optical fiber. This allowed them to increase the stability requirements of the gyroscope by 500 times compared to other fiber optic gyroscopes. ❤
I love your videos and I am the student at FAU 2024. Thanks for everything. 🫶
I love your videos and I am the student at FAU 2024. Thanks for everything. 🫶
I love your videos and I am the student at FAU 2024. Thanks for everything. 🫶
I love your videos and I am the student at FAU 2024. Thanks for everything.
Why do you comment under every video ????
@@user-rh6dc3gq4g because I love their videos duh...
I love your videos and I’m a student at FAU .❤❤
I love your videos and I’m a student at FAU .❤❤
I love your videos and I’m a student at FAU .❤❤
I love your videos and l'm a student at FAU 🫶🫶
I love your videos and l'm a student at FAU 🫶🫶
I love your videos and l'm a student at FAU 🫶🫶
I love your videos and I’m a student at FAU .🫶
I love your videos and I’m a student at FAU . ❤
I love your videos and I’m a student at FAU .
I love your videos and I’m a student at FAU .
I love your videos and I’m a student at FAU
Amazing videos
what is parker weights?
The optimal weight configuration for short scans (180 deg + fan angle): aapm.onlinelibrary.wiley.com/doi/abs/10.1118/1.595078
Vielen Dank!
Sehr gut
owalah ngono to lek
Thank you professor Maier, these lecture recording helps a lot.
Prof. Maier, Thank you very much for sharing your excellent video lecture.
Per the recent developments, are the postulates for pattern recognition still applicable to deep learning today?
Wondering if these limitations are still relevant?
Where's the version without distractions? Thanks for the videos!
hello andreas i am a fan of you
Auf der Folie statistic der Gnerierung von Röntgenstrahlung fehlt hoch n im Zähler des terms
Excellent! Very informative. Vielen Dank!
Hallo Herr Maier, auf der Folie zum Massenschwächungskoeffizienten von Eisen sind Rayleigh und Compton in der Graphik vertauscht. Danke für die tolle Vorlesung!
This is one of greatest lecture on the topic.
I would like to see a new vid on LA. As a working guy, I need to brush up on some things.
We need another Maier unleashed!
Great Talk; Truly insightful!
Very well prepared. Thanks
Can we get the slides?
👌👌👌👌
schönes Video, aber auf einer Folie steht "pulse wave doppler"; gemeint ist aber sicher "pulsed wave doppler"
hat das einen Grund wieso die Vorlesungbzw. die Präsentationauf Englisch ist
Danke fürs anschauliche Erklären der Auflösung!
Hello Prof Andreas Maier, I'm looking forward to do Masters at FAU, Can we talk over LinkedIn?
Clear explanation ❤
The inserts of Elon Musk are already extremely annoying! Unfortunately, this spoils the continuous watching of this video - I scare myself every time I see this face.
Thats how you would explain it... not like in MIPIA :D
woow hat super geholfen, den Stoff zu verstehen 😍 vielen Dank!
Excellent video!!! Thank you.