• Abschlussvortrag Bachelorarbeit, Qasim Sefaldeen
    Exploring the Influences of Different Pruning Methods on the Compressibility of Neural Networks
    October 14, 2024 10:00 - 11:00
    Seminarraum R1307
  • Abschlussvortrag Bachelorarbeit, Lukas Steinmann
    Prozedurale Generierung von Strecken für Autonome Rennfahrzeuge
    October 14, 2024 15:00 - 16:00
    Seminarraum R1307
  • Abschlussvortrag Bachelorarbeit, Henrik Bajon
    Minecraft Architecture Design Using Wave Function Collapse
    October 14, 2024 16:00 - 17:00
    Seminarraum R1307
  • Abschlussvortrag Masterarbeit, Yiming Di
    Multi-objective Optimization of Learning-based Image Codecs using AutoML
    October 15, 2024 16:00 - 17:00
    Seminarraum R1307
  • Abschlussvortrag Masterarbeit, Dennis Roestel
    Integration meteorologischer Vorhersagedaten zur Optimierung der Waldbrandriskioprädiktion
    October 21, 2024 12:00 - 13:00
    Seminarraum R1307
  • Promotionsvortrag, Christoph Reinders, M. Sc.
    Deep Learning With Very Few Training Examples
    November 29, 2024 13:00 - 14:00
    eNIFE, Schneiderberg 32, Hörsaal 031
  • Abschlussvortrag Bachelorarbeit, Florian Fingscheidt
    Ansätze fur die bitrateneffiziente Übertragung von Gewichtsupdates einer DNN-basierten Bildcodierung
    October 10, 2024 16:00 - 17:00
    Seminarraum R1307
  • Konzeptvortrag Masterarbeit, Hans Olbrich, B.Sc.
    Maschinelles Lernen mit modularen Ansätzen zur präzisen Vorhersage von Waldbrandrisiken
    October 10, 2024 10:00 - 11:00
    Seminarraum R1307
  • Konzeptvortrag Masterrarbeit, Telman Shamoyan
    Resolution Enhancement Using Residual Convolutional Neural Networks and Contact Matrix Properties
    October 10, 2024 11:00 - 12:00
    Seminarraum R1307
  • Abschlussvortrag Bachelorarbeit, Lukas Knölker
    Heuristical Search for Nash Equilibria by Support Enumeration
    September 26, 2024 09:00 - 10:00
    Seminarraum R1307
  • May 07 - - July 07, 2024
    Der Girls’Day – Mädchen-Zukunftstag ist ein bundesweites Projekt zur Berufs- und Studienorientierung von Mädchen. Am alljährlichen Aktionstag lernen Schülerinnen Berufe oder Studienfächer kennen, in denen der Frauenanteil unter 40 Prozent liegt. Am 25. April 2024 bekamen die Teilnehmerinnen zwischen 09:00 - 15:00 Uhr erneut die Gelegenheit, die Welt einer Wissenschaftlerin aus verschiedenen Standpunkten zu sehen. Gemeinsam mit dem Institut für künstliche Intelligenz beteiligten wir uns mit einem vielseitigen Angebot zu den Bereichen Bilderkennung, Chatbots und der künstlichen Intelligenz in Spielen. Zudem gaben die Forschenden Einblicke in ihren Alltag und beantworteten viele Fragen zur Anwendung und Funktionsweise von Künstlicher Intelligenz. Wir hatten eine Menge Spaß und freuen uns bereits auf das kommende Jahr. Wir bedanken wir uns bei allen Teilnehmerinnen und Mitwirkenden!


  • December 07, 2023 - March 07, 2024
    At this year's "Day of the Faculty", the jury of the "APFEL-Preis für exzellente Lehre" awarded our Junior Professor Alexander Dockhorn the prize in the Lecture/Seminar category for his particularly strong commitment to the course and sincere interest in the students.


  • July 25 - - October 23, 2023
    TNT was founded 50 years ago. Current and former members of TNT will join us for a workshop on October 13th, 2023.


  • July 25 - - October 25, 2023
    Our lab has a long tradition in contributing the international standards like mp3, AAC, MPEG-1, MPEG-2, AVC, HEVC, VVC, DASH and MPEG-G defined by the Moving Pictures Experts Group (MPEG), also known as ISO/IEC JTC1/SC29/WG2,3,4,5,6,7,8, and 11. From October 13th to October 19, this group will meet for its 144th meeting in Hannover. It is the third time after 1988 and 2008 that MPEG with its more than 400 researchers comes to Hannover and TNT.


  • May 15, 2023
    Our work Compensation Learning in Semantic Segmentation will be presented at The 2nd Workshop Challenge on Vision Datasets Understanding (VDU) at The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (CVPR)

  • April 25 - - October 25, 2023
    Our work POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning has been accepted at the Transactions on Machine Learning Research (TMLR)!


  • March 30 - - April 30, 2023

    Our joint work Semantic Segmentation for Fully Automated Macrofouling Analysis on Coatings after Field Exposure was accepted to Biofouling. Thanks for the great effort to our colleagues from Ruhr-Univerisität Bochum and Florida Tech! Code is available on Github.



  • February 07, 2023
    The TNT is excited to announce that we are part of the Horizon Europe funded project Satellites for Wilderness Inspection and Forest Threat Tracking (SWIFTT). The project's goal is to develop powerful machine learning models as a backend for a platform which helps forest managers to detect threats to their forests in an affordable and simple manner. SWIFTT will be based on the remote sensing data provided by the Copernicus programme. The TNT's primary role will be developing a model for wildfire risk prediction at a high spatial resolution. SWIFTT's first press release can be found here.


  • January 30 - - June 15, 2023
    Our paper Deep Reinforcement Learning for Autonomous Driving using High-Level Heterogeneous Graph Representations has been accepted to ICRA 2023! You can find the accepted version here. Our implementation is published here.


  • December 02, 2022
    Using personalized medicine to combat depression—we are part of the largest German study to improve depression treatment. Using biomarkers to find individual diagnosis and therapy paths—what already works in oncology should also become possible in psychiatry. Under the leadership of the Hannover Medical School (MHH), a national research network is now being launched that aims to tailor the treatment of depression more closely to the individual patient than before. The project, entitled “Personalized, Predictive, Precise and Preventive Medicine to Improve Early Detection, Diagnosis, Therapy and Prevention of Depressive Disorders” (P4D), aims to develop individualized treatment approaches. Click here for the full press release (in German).


  • December 13, 2021 - March 31, 2022


  • April 22 - - May 31, 2021
    AutoML@ICML'21: We co-organize the AutoML workshop at the international conference on machine learning (ICML) 2021. In the last years, it was one of the biggest workshops at ICML. For more information visit http://icml2021.automl.org/.


  • February 18 - - December 18, 2021
    VCIP 2021: We organize the VCIP 2021 chaired by Jörn Ostermann and Touradj Ebrahimi in Munich. VCIP is one of the oldest IEEE conferences in the field of visual communications and image processing. Since 1986, VCIP has served as a premier forum for the exchange of fundamental and applied research in the field of visual communications and image processing. For more information visit www.vcip2021.org.


  • March 05, 2020
    Paper accepted to ICRA 2020: Temporally Consistent Horizon Lines. Source code and dataset are available on GitHub!


  • March 05, 2020
    Paper accepted to CVPR 2020: CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus. Source code and dataset are available on GitHub!


  • February 14, 2020

    Student team successful in AI competition Battlecode

    Our students Hannes Küttner, Simon Reuß und Maximilian Schier have successfully participated in the AI competition Battlecode. Battlecode is an international real-time strategy game organized by MIT. Over four weeks the students developed AIs within our lab Machine Learning for Games AIs which is supervised by Christoph Reinders and Frederik Schubert. The team qualified as one of the best four international teams for the final, which took place at MIT in Boston/Cambridge. In the final the team took 7th place from over 600 student teams that competed worldwide.

    Battlecode Team


  • December 06, 2019

    55. Working Group of Initiative Bildverarbeitung e. V. at TNT

    The TNT hostet the 55. working group (55. Arbeitskreis) of the Initiative Bildverarbeitung e. V. ("Inititative Image Processing, registered association"). Employees of the TNT presented their research in demo sessions as well as presentations. The event was closed by an overview of the activities of the Viscoda GmbH by its Managing Director Dr.-Ing. Hellward Broszio. A more detailed report about the 55. working group can be found at here [German].




  • December 05, 2019

    KI Talent Award

    Our student Tom Wehrbein received the "KI Talent" award for his bachelor thesis "Representation of Human Motion using Neural Networks". With the award the Niedersächsisches Ministerium für Wirtschaft, Arbeit, Verkehr und Digitalisierung (MW) honors excellent works in the field of artificial intelligence.




  • October 18, 2019

    Visit by Delegation from NCTU University in Taiwan

    In October 2019, our lab was visited by a delegation of professors from NCTU university in Taiwan.

    Prof. Hsueh-Ming Hang, Prof. Wen-Hsiao Peng and Prof. Hsu-Feng Hsiao gave presentation about the research of their groups. Their research topics are centered around, deep-learning based image compression and segmentation, reinforcement learning for video encoder control and video prediction, and learning based salient object detection and perceptual quality analysis.

    In reply, five researches of our lab introduced our research. Together, we discussed the presented research topics.




  • September 20, 2019

    Klausurtagung 2019

    For our annual lab retreat, all professors and PhD students of TNT as well as several students went to Goslar. For five-days we discussed our current research projects as well as new ideas.




  • May 13, 2019

    Research Visit at TNT (bachelor thesis)

    Yichun He and Youzhi Luo from the University of Science and Technology of China

    Students


  • March 08, 2019

    2nd Place at Battlesnake 2019

    At this year's Battlesnake competition in Victoria BC, Canada, our student team consisting of Maximilian Schier, Niclas Wüstenbecker and Frederik Schubert finished second in the intermediate category.
    Their snake AI, which they nicknamed "Niedersächsische Kreuzotter", was developed as part of our Video Game AI project supervised by Florian Kluger.

    All their matches, including the decisive final, can be rewatched on Twitch:

    Battlesnake Team
    Maximilian and Niclas (centre) together with the other finalists.



  • February 02, 2019

    Our Battlecode team has made it into the top 10

    Our student team consisting of Niclas Wüstenbecker, Paul Hindricks, and Maximilian Schier was very successful in the international competition Battlecode. Battlecode is an international real-time strategy game organized by MIT. The team developed their bot within our lab Machine Learning for Games AIs which is supervised by Christoph Reinders. They qualified for the final which took place at MIT in Boston/Cambridge and made it into the top 10. Congratulations to the team!

    Battlecode Team


  • December 21, 2018

    Road Damage Detection Challenge Award

    The joined work Region-based Cycle-Consistent Data Augmentation for Object Detection from Ignaris, Henschel & Wandt and TNT has been awarded with a Special Price for proposing innovative ideas and contributing to the Road Damage Detection Challenge Workshop at IEEE Big Data 2018.
    Special Price


  • December 10, 2018

    2nd place at IEEE Hackathon on personalized medicine

    Florian Kluger and Christoph Reinders made it to the 2nd place at the IEEE Hackathon at IEEE Big Data Governance and Metadata and Management Workshop.

    Award Christoph
    Award Florian


  • July 09, 2018

    4th Summer School on Video Compression and Processing (SVCP)

    We organized the 4th Summer School on Video Compression and Processing (SVCP) from 4-6 July which took place at Parkhotel Bilm in Sehnde near Hannover. During the three days of the Summer School we heard very interesting talks from all participants and discussed about current research projects and future research avenues. We also enjoyed an inspiring keynote from Bodo Rosenhahn who shed light on the pros and cons of the current hype on machine learning and neural networks.

    We thank all participants for the fruitful discussions and we are looking forward to the continuation of this series of summer schools.




  • October 17, 2017

    Besuch bei Daimler in Wörth

    Prof. Ostermann und Mitarbeiter des Instituts für Informationsverarbeitung (TNT) besuchten im Rahmen eines gemeinsamen Projektes am 12.10.2017 das Entwicklungs- und Versuchszentrum (EVZ) für Lkw vom Mercedes-Benz-Werk Wörth.
    Neben der Präsentation einer studentischen Arbeit, die vom TNT mitbetreut wird, gab es eine spannende Demonstration des Active Brake Assist 4 (ABA4) Systems (Video ABA4)


  • July 28, 2017

    CVPR 2017 Challenge Award

    Our paper Improvements to Frank-Wolfe optimization for multi-detector multi-object tracking wins the CVPR 2017 Challenge in Multiple Object Tracking. Congrat's to Roberto Henschel and Bodo Rosenhahn.

    CVPRAward2017


  • May 03, 2017

    Best Paper Award at Eurographics 2017

    Our presented paper Sparse Inertial Poser: Automatic 3D Human Motion Capture from Sparse IMUs received the Günter Enderle Award for the Best Paper at Eurographics 2017. Congrat's to Timo v. Marcard, Bodo Rosenhahn, Michael J. Black and Gerard Pons-Moll.

    EurographicsBestPaperAward2017 EurographicsBestPaperAward2017Cermony


  • March 02, 2017

    Chinese Exchange Students 2017

    Following a multiple years-long tradition, several exchange students from the University of Science and Technology of China located in Hefei, China, are visiting our lab during this spring. Upon their arrival, they were greeted by the head of Insitut für Informationsverarbeitung, Jörn Ostermann. The four students Yichen Wang, Yanxin Xi, Liuyu Xiang, and Xu Han will be involved in several research projects to which they will contribute actively.


  • October 04, 2016

    Klausurtagung 2016

    In the last week of September, the professors and PhD students of TNT as well as several undergraduate students went to Kassau for our annual five-day lab retreat. We discussed our current research projects and other matters of interest.


    klausurtagung


  • August 31, 2016

    Freiwilliges Wissenschaftliches Jahr 2015/2016 (FWJ)

    Ricarda Theis and Elias Krey finished their one year-long FWJ (Freiwilliges Wissenschaftliches Jahr) at Institut für Informationsverarbeitung of Leibniz Universität Hannover. During their year they dipped into the very diverse research projects at TNT and realized their own application-oriented projects.

    Ricarda built a step counter for rope skipping sports and Elias built a radar sensor for a SAR demonstrator.

    FWJ projects in 2016


  • August 29, 2016

    Winner of the pi2run

    The TNT won the 1st price in the pi2run relay race organized by the IfES in the category 'mixed'. Congrat's to our runners Hilke Brodersen, Stella Graßhof, Thomas Krause and Bastian Wandt!


    pi2run during the race


  • July 18, 2016


  • May 24, 2016

    Chinese exchange students 2016

    As in previous years, multiple exchange visitors from the University of Science and Technology of China located in Hefei, China, visited our lab. The four students (Zou Xiating, Li Ren, Xie Xianda and Ren Zeping) were involved in several research projects to which they contributed actively. They finished their internships successfully in May 2016.

    Chinese exchange visitors



  • July 10, 2015

    Ideenexpo 2015

    Das TNT auf der Ideenexpo 2015. Timo von Marcard und Florian Baumann betreuen das Zukunftsmobil der Fakultät und erklären Schülern die verschiedenen Exponate. Kommt uns besuchen!

    Zukunftsmobil auf der Ideenexpo



  • July 07, 2015

    Baker Hughes Excursion 2015

    On tuesday july 7th Prof. Ostermann, Marco Munderloh and Yasser Samayoa of the TNT took 15 students of the Leibniz Universität Hannover on an excursion to the Baker Hughes Inteq GmbH in Celle. After an introduction about the company and technical presentations the students were able to visit the production- and research facilities and see some live demonstration of recently developed communications engineering systems.


  • July 01, 2015

    Technicolor Excursion 2015

    On Wednesday July 1st Hendrik Hachmann, Bastian Wandt and Felix Kuhnke of the TNT took 14 students from the Leibniz Universität Hannover on an excursion to the Technicolor Research & Innovation Center Hannover. After a presentation about facts and figures on Technicolor and a special effects demonstration of MPC the students were able to get in contact with different departments which were presenting their research on audio processing, scenic analysis, genetic coding and alpha matting. The excursion ended with a cozy wrap up including food and beverages.


  • March 02, 2015

    Messe Beruf und Bildung 2015

    Das TNT auf der Beruf und Bildungsmesse 2015 in der Eilenriedehalle in Hannover. Timo von Marcard und Florian Baumann betreuen das Zukunftsmobil der Fakultät und erklären Interessierten die verschiedenen Exponate.

    Zukunftsmobil auf der Messe Beruf und Bildung



  • January 09, 2015

    WACV 2015 Challenge Award

    Der Beitrag "Solving Multiple People Tracking In A Minimum Cost Arborescence", mit dem Roberto Henschel et al. beim "1st Workshop on Benchmarking Multi-target Tracking" angetretten ist, erreichte den 2ten Platz und wurde mit dem WACV 2015 Challange Award ausgezeichnet.


  • December 15, 2014

    Research stay at Disney Research, Pittsburgh

    Alina Kuznetsova did a research stay at Disney Research, Pittsburgh, one of the top research labs in the world. She was working on object detection in videos using domain adaptation techniques, under supervision of Dr. Sung Ju Wang and Dr. Leonid Sigal.


  • November 12, 2014

    KISS ME 2014

    Das TNT auf der Firmenkontaktmesse KISSME im Lichthof der Uni. Petrissa, Stella, Paul, Thomas und Florian präsentieren das TNT auf der KISS ME und suchten Absolventen zur Unterstützung unseres Teams und Studenten für Abschlussarbeiten.

    KISSME 2014



  • February 27, 2014

    Wissenschaftspreis 2013/2014

    Zeitungsartikel Uni Präsident Prof.Dr.-Ing. Erich Barke überreichte am 26.02.2014 Dipl.-Ing. Holger Zernetsch (IMP) und Dipl.-Ing. Florian Baumann (TNT) den Wissenschaftspreis für das Spin-Off HearingCampus für die beste Geschäftsidee.
    Geschäftsidee ist eine App, mit der Jedermann zuhause sein eigenes Gehör testen kann. Die Möglichkeiten gehen dabei über einen normalen Hörtest hinaus: so kann mit der Lösung auch das Verständnis von Silben und Zahlen untersucht werden. Außerdem kann direkt aus der App heraus Kontakt zu einem Hörgeräteakustiker in der Nähe aufgebaut werden, wenn eine Hörminderung festgestellt werden sollte. Der Akustiker kann dann das zuvor mit der App erstellte Hörprofil auf Wunsch des Kunden auslesen und als Grundlage für die Einstellung von Hörgeräten verwenden. So sparen beide Seiten Zeit und es kann eine optimale Anpassung auf die Hörbedürfnisse des Kunden vorgenommen werden - bestehende Hörgeräteträger können die App nutzen, um ihr Hörvermögen laufend zu untersuchen und wenn nötig die Einstellungen ändern lassen. Dies schafft effektivere Arbeitsprozesse für den Akustiker und erhöht gleichzeitig die Zufriedenheit der Kunden. Die beiden Gründer agieren dabei als unabhängiges Bindeglied zwischen beiden Gruppen.



  • August 24 - 31, 2013
    Bild IdeenExpo 2013

    Ideen Expo 2013

    Vom 24. bis zum 31. August stellt das TNT einen Gesichtstracker aus, der das Gesicht vor der Kamera über einem Bildschirm verfolgt. Mit geschickter Kopfbewegung lässt sich dann eine virtuelle Kugel durch einen Irrgarten rollen. Der schnellste Schüler am Freitag war Mark.

    Die Fakultät für Elektrotechnik und Informatik hat sich mit drei Exponaten auf der Ideenexpo beteligt.
    Das Institut für Echtzeitsysteme zeigte auf einer sogenannten Experimentierstation ein Video mit symbolisierten Ameisen im Wettbewerb mit anderen Stämmen bei der Nahrungsaufnahme. Das Institut für Theoretische Informatik hat ein Brett mit aufgemaltem Graphen und Bändern zur Simulation des maximalen Flusses ausgelegt.



  • May 22, 2013

    SFB 653 extended

    We are proud to announce the extension of the Sonderforschungsbereich 653 "Gentelligent components in the life cycle" for another 4 years. The overall funding is 9mio. EUR spread over 17 subprojects, in which 10 institutes from both the electrical and the mechanical engineering departments participate. The goal of SFB 653 is to create mechanical components that are able to "feel" and record their entire life cycle in order to continuously optimize newer generations of the same component.

    The TNT contributes to this interdisciplinary collaboration with its strong expertise in signal processing and pattern recognition. Helping the SFB's vision of a self-controlled cradle-to-cradle monitoring, Dipl.-Ing. Benjamin Spitschan works on self-identification and counter-plagiasm technologies, enabling individual mechanical components to securely authenticate themselves during the manufacturing and use phases.


  • April 22 - 29, 2013

    TNT-Student participates at MPEG meeting

    Our student Thorsten Laude participates at the 104th MPEG meeting in Incheon, South Korea. Since the beginning of MPEG standardization, we contribute to the standardization of digital audio and video codecs like MP3 (iPod), MPEG-2 (DVD, DVB-T), AVC/H.264 (Mobile phone, PC, HDTV over satellite, cable or DSL). Thorsten's work is relevant for the current standardization of the next generation video codec HEVC and SHVC.


  • January 16 - 18, 2013

    TNT-Student participates at WACV 2013

    Our student Oliver-Jakob Arndt participates at the IEEE Workshop on Applications of Computer vision (WACV) in Clearwater Beach, Florida, USA. At the workshop Jakob will present the paper "Region Cut" - Interactive Multi-Label Segmentation Utilizing Cellular Automaton, which proposes a novel Segmentation scheme. The proposed method arose during his two year student assistance job in our Lab.


  • July 01 - - October 05, 2012

    Research stay at Microsoft Research, Cambridge

    Gerard Pons-Moll did a research stay at Microsoft Research, Cambridge one of the top research labs in the world. He was working on human pose estimation from Kinect data. Part of the work conducted during this time was published at BMVC 2013, "Metric Regression Forests for Human Pose Estimation" which received the best science paper award.


  • March 30, 2012

    Students test TNT-App

    Bild Smart Phone At TNT we developed an advanced face detection app for smart phones. It is another application that increases the usefulness of our daily companion.


  • January 01 - - November 30, 2012

    Research stay at the University of Michigan

    Laura Leal-Taixé did a one year research stay at the University of Michigan, Ann Arbor, one of the top technical universities in the United States. She was at the Vision Lab working with Prof. Silvio Savarese on multiple people tracking in semi-crowded scenarios. Her research was focused on learning pedestrian behaviors from images using machine learning.


  • January 01 - - June 16, 2012

    Research stay at the University of Toronto

    Gerard Pons-Moll did a research stay at the University of Toronto, one of the top world universities in computer science. He was at the Computer Vision Lab working with Prof. David Fleet. Part of the work conducted during this time was published at CVPR 2014, "Posebits for Monocular Human Pose Estimation"


  • September 02, 2011

    Die Europäische Kommission fördert Prof. Rosenhahn mit 1,3 Millionen Euro

    Am Institut für Informationsverarbeitung wird Prof. Bodo Rosenhahn mit seinem Projekt im Bereich "Maschinensehen“ forschen. Es geht darum, wie man Fähigkeiten des menschlichen visuellen Systems auf einen Computer (ausgestattet mit einer Kamera) übertragen kann. Insbesondere das Erkennen dynamischer Szenen, beispielsweise menschlicher Bewegungen, soll dabei erforscht werden. Diese Projekt wird durch das Excellenzprogramm des European Research Councils mit 1,3 Millionen Euro über fünf Jahre gefördert. Dies ist für Prof. Rosenhahn und die Fakultät ein riesiger Erfolg.
    Der Europäische Forschungsrat fördert insbesondere hochkarätige grundlagenorientierte und visionäre Forschung. Die wissenschaftliche Exzellenz ist dabei das entscheidende Kriterium. Die Konkurrenz in diesem Programm ist sehr hoch, die Bewilligungsquote liegt bei unter zehn Prozent der eingegangenen Anträge.


  • June 20 - 25, 2011

    TNT-Student participates at CVPR 2011

    Our bachelor student Hamon Riazy participates at the seventh IEEE workshop on Embedded Computer Vision (ECVW2011) in Colorado Springs, Colorado, USA. The workshop is part of the IEEE Conference on Computer Vision and Pattern Recognition. At the workshop we present the paper "Ego-Motion Compensated Face Detection on a mobile device". The paper directly follows Hamon's bachelor thesis.


  • April 19 - 23, 2010

    92nd MPEG Meeting in Dresden

    TNT hosted the 92nd MPEG meeting in Dresden. Despite the partial closure of the European airspace due to the eruption of Eyjafjallajökull, 200 of 280 participants started the work on the upcoming video coding standard HEVC and the Advanced IPTV Terminal. The other participants made further progress the standards relating to MPEG-Audio and MPEG-Systems.

    One member showed special dedication to the standardization work: Flying from Seoul via the Emirates to Rome, he rented a car to go to Torino. In Torino, he convinced a colleagues to drive him to Dresden where he arrived after the 60h trip.

    The press release does not mention the social event on Wednesday resulting in a remarkable video showing the technology developed by MPEG: The Zig-zag Scan.



  • February 10, 2010

    Technical Emmy Award für MPEG-4 Advanced Video Coding im Institut angekommen

    Am 7.1.2009 wurde in Las Vegas der „Technology and Engineering Emmy Award 2007- 2008“ für die Entwicklung des neuen Videokompressionsverfahrens MPEG-4 AVC (Advanced Video Coding) verliehen. Der Preis ging an die Moving Picture Experts Group (MPEG) und die Video Coding Experts Group (VCEG), die den internationalen Standard gemeinsam mit Beteiligung des TNT entwickelt hatten.


  • October 05, 2009

    Forschungsaufenthalt in der Industrie

    Unser wissenschaftlicher Mitarbeiter Dipl.-Math. Nikolce Stefanoski kehrt von einem dreimonatigen Forschungsaufenthalt bei Disney Research in Zürich zurück.


  • September 05 - 13, 2009
    Bild Shoaib

    Ideen Expo 2009

    Vom 5. bis zm 13. September stellten Ralf Dragon und Muhammad Shoaib unser Kamerasystem mit automatischer Personenverfolgung und die lernende Erkennungssoftware aus. Besonders gerne wurden Geldscheine als zu erkennende Objekte von den vielen Besuchern eingesetzt.


  • July 01, 2009

    Forschungsaufenthalt in der Industrie

    Unser Mitarbeiter Herr Sven Klomp kehrt von einem dreimonatigem Forschungsaufenthalt bei Mitsubishe Electri Research Labs (MERL), Boston, MA, USA, zurück.


  • May 04, 2009

    Conference on 3DTV in Potsdam

    TNT hosted 3DTV-CON 2009, The True Vision - Capture, Transmission and Display of 3D Video in Potsdam. Almost 200 participants showed their latest results on 3D video analysis, coding, streaming and applications.


  • May 03 - 31, 2009

    Forschungsaufenthalt in Rio

    Im Rahmen eines Forschungsaufenthalts besucht unser Mitarbeiter Thorsten Büschenfeld die Pontifical Catholic University of Rio de Janeiro . Die automatische Luftbildauswertung ist aufgrund der illegalen Abholzung wichtiger Waldflächen ein Forschungsschwerpunkt in Brasilien. Die am TNT entwickelte Software GeoAida wird von brasilianischen Universitäten und Regierungsorganisationen genutzt.


  • July 21 - 25, 2008

    MPEG in Hannover

    Das 85. Treffen der ISO/IEC JTC1 Sc29/WG11 (MPEG) und das Joint Video Team trafen sich vom 21. bis zum 25. July 2008 auf Einladung des TNT in Hannover. Etwa 250 Experten entwickelten die Standards im Bereich Audio, Video und Grafik weiter. Während der Woche wurde vom TNT entwickelte Technologie für die effiziente Codierung und Übertragung von animierten Netzen in den Standard MPEG-4 aufgenommen.


  • September 15, 2023

    Best Presentation Award

    AwardeeFabian Müntefering, Jörn Ostermann, Jan Voges
    Prizewinner: Fabian Müntefering, Jörn Ostermann, Jan Voges
    For the oral presentation: BACON: Bacterial Clone Recognition from Metagenomic Sequencing Data
    Award Sponsor: AICPM 2023


  • April 01, 2021

    First Place Student Paper Award

    AwardeeAron Sommer, Jörn Ostermann
    Prizewinner: Aron Sommer, Jörn Ostermann
    For his/her work: Analysis of Ship Deformation using the Backprojection Autofocus of Large Ships with Arbitrary Motion for Synthetic Aperture Radar
    Award Sponsor: EUSAR 2021


  • December 11, 2020

    1st and 3rd at BBO-Challenge@NeurIPS'20

    Prizewinner: Difan Deng and Marius Lindauer et al.
    AutoML.org & IOHprofiler, featuring the switching squirrel. After fixing a minor bug, our Switching Squirrel achieved a strong 3rd place at the black-box challenge at #NeurIPS2020 (#AutoML and Hyperparameter Optimization). On the warm-start friendly leaderboard, our Squirrel was even ranked 1st and was awarded an extra prize money. Our Squirrel combines ideas from (i) (simple) meta-learning by recognizing known configuration spaces, (ii) a diverse portfolio of acquisition functions, surrogate models and data transformations for Bayesian Optimization and (iii) differential evolution for a greedy final stage. It is the outcome of a joint collaboration between the groups from AutoML.org (tnt@Leibniz University Hannover and University of Freiburg) and IOHProfiler (Leiden University and Sorbonne University). Competition homepage


  • October 23, 2020

    Best Student Paper Award

    AwardeeMaren Awiszus, Frederik Schubert and Bodo Rosenhahn
    Prizewinner: Maren Awiszus, Frederik Schubert and Bodo Rosenhahn
    Award Sponsor: AIIDE 2020


  • November 20, 2020

    1st and 2nd places at ABAW-Competition

    Prizewinner: Felix Kuhnke, Lars Rumberg, Jörn Ostermann
    In the FG-2020 Competition: Affective Behavior Analysis in-the-wild (ABAW) researchers from TNT achieved two strong 2nd places (for action unit and valence arousal estimation) and one 1st place for categorical emotion recognition. The goal of this competition was to extract human emotion from "in-the-wild" videos. Our work was presented at the IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2020, 16-20 November 2020.
    Award Sponsor: https://ibug.doc.ic.ac.uk/resources/fg-2020-competition-affective-behavior-analysis/


Alle Auszeichnungen anzeigen