Montag, 20. November 2017

[HIForum] [Kolloquium] REMINDER: Informatics Colloquium, today, Monday 20 Nov, 17:15, B-201

_______________________________________________
Kolloquium mailing list
Kolloquium@mailhost.informatik.uni-hamburg.de
https://mailhost.informatik.uni-hamburg.de/mailman/listinfo/kolloquium_______________________________________________
Dear all,
May we kindly remind you of the today's talk with Prof. Dr. Jürgen Gall at 17:15 in room B-201 (Stellingen Campus). Please find the details below.
Best regards
Stephanie Schulte Hemming


Von: Fbi-alle [fbi-alle-bounces@mailhost.informatik.uni-hamburg.de]" im Auftrag von "Schulte Hemming, Stephanie [schulte@informatik.uni-hamburg.de]
Gesendet: Dienstag, 7. November 2017 11:20
An: kolloquium@informatik.uni-hamburg.de
Betreff: [Fbi-alle] [Kolloquium] INVITATION: Informatics Colloquium 20 Nov 2017 17:15 B-201

This is an invitation to the next Informatics Colloquium on Monday, 20 November 2017, 17:15, Campus "Informatikum/Stellingen", Room B-201The talk entitled "Analyzing Human Behavior in Video Sequences" will be held by Prof. Dr. Jürgen Gall, Professor at the University of Bonn, Institute of Computer Science III, Computer Vision Group.

                

This talk will be held in English. The colloquium committee is looking forward to seeing you all there and to sharing this talk with you. For details on the series of colloquiums planned, please visit https://www.inf.uni-hamburg.de/home/kolloquium/wise17-18.html

 

On behalf of the colloquium committee

Stephanie Schulte Hemming

Universität Hamburg

 

 

ABSTRACT:

Analyzing the behavior of humans in continuous video recordings is still a very difficult task. In the fully supervised setting, temporal models like RNNs are trained on videos that are annotated at a frame-level. Acquiring such annotations, however, is very time consuming and strong temporal models require large amounts of annotated training data. Weaker forms of supervision like transcripts are therefore investigated to learn temporal models. In this talk, I will describe some of our recent works on weakly supervised learning of actions and I will give an overview of the research activities that are conducted within the DFG research unit "Anticipating Human Behavior" at the University of Bonn.

 

BIO:

Prof. Dr. Juergen Gall is professor and head of the Computer Vision Group at the University of Bonn since June 2013. After his Ph.D. in computer science from the Saarland University and the Max Planck Institut für Informatik, he was a postdoctoral researcher at the Computer Vision Laboratory, ETH Zurich, from 2009 until 2012 and senior research scientist at the Max Planck Institute for Intelligent Systems in Tübingen from 2012 until 2013. He received a grant for an independent Emmy Noether research group from the German Research Foundation (DFG) in 2013, the German Pattern Recognition Award of the German Association for Pattern Recognition (DAGM) in 2014, and an ERC Starting Grant in 2016. He is further spokesperson of the DFG funded research unit "Anticipating Human Behavior" at the University of Bonn since 2017.

  

CONTACT:

Prof. Dr. Simone Frintrop, Universität Hamburg, FB Informatik

 

 

 

 

 

Dienstag, 7. November 2017

[HIForum] [Kolloquium] INVITATION: Informatics Colloquium 20 Nov 2017 17:15 B-201

This is an invitation to the next Informatics Colloquium on Monday, 20 November 2017, 17:15, Campus "Informatikum/Stellingen", Room B-201The talk entitled "Analyzing Human Behavior in Video Sequences" will be held by Prof. Dr. Jürgen Gall, Professor at the University of Bonn, Institute of Computer Science III, Computer Vision Group.

                

This talk will be held in English. The colloquium committee is looking forward to seeing you all there and to sharing this talk with you. For details on the series of colloquiums planned, please visit https://www.inf.uni-hamburg.de/home/kolloquium/wise17-18.html

 

On behalf of the colloquium committee

Stephanie Schulte Hemming

Universität Hamburg

 

 

ABSTRACT:

Analyzing the behavior of humans in continuous video recordings is still a very difficult task. In the fully supervised setting, temporal models like RNNs are trained on videos that are annotated at a frame-level. Acquiring such annotations, however, is very time consuming and strong temporal models require large amounts of annotated training data. Weaker forms of supervision like transcripts are therefore investigated to learn temporal models. In this talk, I will describe some of our recent works on weakly supervised learning of actions and I will give an overview of the research activities that are conducted within the DFG research unit "Anticipating Human Behavior" at the University of Bonn.

 

BIO:

Prof. Dr. Juergen Gall is professor and head of the Computer Vision Group at the University of Bonn since June 2013. After his Ph.D. in computer science from the Saarland University and the Max Planck Institut für Informatik, he was a postdoctoral researcher at the Computer Vision Laboratory, ETH Zurich, from 2009 until 2012 and senior research scientist at the Max Planck Institute for Intelligent Systems in Tübingen from 2012 until 2013. He received a grant for an independent Emmy Noether research group from the German Research Foundation (DFG) in 2013, the German Pattern Recognition Award of the German Association for Pattern Recognition (DAGM) in 2014, and an ERC Starting Grant in 2016. He is further spokesperson of the DFG funded research unit "Anticipating Human Behavior" at the University of Bonn since 2017.

  

CONTACT:

Prof. Dr. Simone Frintrop, Universität Hamburg, FB Informatik

 

 

 

 

 

Montag, 6. November 2017

[HIForum] [Kolloquium] FW: [Fbi-alle] [CML] CML/Informatics Colloquium, November 6th, 2017, 5pm

Dear all,
May we kindly remind you of the today's talk with Prof. Frank Keller at 17:15 in room D-125 (Stellingen Campus). Please find the details below.
Best regards
Stephanie Schulte Hemming


Am [DATE] schrieb "Fbi-alle im Auftrag von Wolfgang Menzel" <[ADDRESS]>:


You are cordially invited to the joint CML/Informatics Colloquium
taking place in Room D-125 on the Stellingen Campus,
Vogt-Kölln-Strasse 30 on

                     November 6th, 2017, 5pm.

Frank Keller, Professor in the School of Informatics at the
University of Edinburgh, will give a talk on

              Jointly Representing Images and Text:
     Dependency Graphs, Word Senses, and Multimodal Embeddings

Abstract:

In this presentation, I will argue that we can make progress in
language/vision tasks if we represent images in structured ways,
rather than just labeling objects, actions, or attributes. In
particular, deploying structured representations from natural language
processing is fruitful: I will discuss how visual dependency
representations (VDRs), which borrow ideas for dependency parsing, can
be used to capture how the objects in an scene interact with each
other. VDRs are useful for tasks such as image retrieval or image
description. Secondly, I will argue that much more fine-grained
representations of actions are needed for most language/vision
tasks. Again, ideas from NLP are be leveraged: I will introduce
algorithms that use multimodal embeddings to perform verb sense
disambiguation in a visual context.

Bio:

Frank Keller is professor of computational cognitive science in the
School of Informatics at the University of Edinburgh. His background
includes an undergraduate degree from Stuttgart University, a PhD from
Edinburgh, and postdoctoral and visiting positions at Saarland
University and MIT. His research focuses on how people solve complex
tasks such as understanding language or processing visual information.
His work combines experimental techniques with computational modeling
to investigate reading, sentence comprehension, and language
generation, both in isolation and in a visual context. Prof. Keller
serves on the management committee of the European Network on Vision
and Language, is a member of governing board of the European
Association for Computational Linguistics, and recently completed an
ERC grant in the area of vision and language.


*********************************************************************
Wolfgang Menzel                    Universitaet Hamburg
                                   Fakultaet fuer Mathematik,
                                   Informatik und Naturwissenschaften
                                   Fachbereich Informatik
                                   AB Natuerlichsprachliche Systeme
menzel@informatik.uni-hamburg.de   Vogt-Koelln-Strasse 30
phone: (49-40) 428 83 - 24 35      D-22527 Hamburg
**********************************************************************

_______________________________________________
Kolloquium mailing list
_______________________________________________

Dienstag, 24. Oktober 2017

[HIForum] [Kolloquium] [CML] [Fbi-alle] CML/Informatics Colloquium, November 6th, 2017, 5pm

You are cordially invited to the joint CML/Informatics Colloquium
taking place in Room D-125 on the Stellingen Campus,
Vogt-Kölln-Strasse 30 on

November 6th, 2017, 5pm.

Frank Keller, Professor in the School of Informatics at the
University of Edinburgh, will give a talk on

Jointly Representing Images and Text:
Dependency Graphs, Word Senses, and Multimodal Embeddings

Abstract:

In this presentation, I will argue that we can make progress in
language/vision tasks if we represent images in structured ways,
rather than just labeling objects, actions, or attributes. In
particular, deploying structured representations from natural language
processing is fruitful: I will discuss how visual dependency
representations (VDRs), which borrow ideas for dependency parsing, can
be used to capture how the objects in an scene interact with each
other. VDRs are useful for tasks such as image retrieval or image
description. Secondly, I will argue that much more fine-grained
representations of actions are needed for most language/vision
tasks. Again, ideas from NLP are be leveraged: I will introduce
algorithms that use multimodal embeddings to perform verb sense
disambiguation in a visual context.

Bio:

Frank Keller is professor of computational cognitive science in the
School of Informatics at the University of Edinburgh. His background
includes an undergraduate degree from Stuttgart University, a PhD from
Edinburgh, and postdoctoral and visiting positions at Saarland
University and MIT. His research focuses on how people solve complex
tasks such as understanding language or processing visual information.
His work combines experimental techniques with computational modeling
to investigate reading, sentence comprehension, and language
generation, both in isolation and in a visual context. Prof. Keller
serves on the management committee of the European Network on Vision
and Language, is a member of governing board of the European
Association for Computational Linguistics, and recently completed an
ERC grant in the area of vision and language.


*********************************************************************
Wolfgang Menzel Universitaet Hamburg
Fakultaet fuer Mathematik,
Informatik und Naturwissenschaften
Fachbereich Informatik
AB Natuerlichsprachliche Systeme
menzel@informatik.uni-hamburg.de Vogt-Koelln-Strasse 30
phone: (49-40) 428 83 - 24 35 D-22527 Hamburg
**********************************************************************

_______________________________________________
Kolloquium mailing list
Kolloquium@mailhost.informatik.uni-hamburg.de
https://mailhost.informatik.uni-hamburg.de/mailman/listinfo/kolloquium
_______________________________________________
HiForum-Verteiler mailing list
HiForum-Verteiler@mailhost.informatik.uni-hamburg.de
https://mailhost.informatik.uni-hamburg.de/mailman/listinfo/hiforum-verteiler

Montag, 17. Juli 2017

[HIForum] [Kolloquium] REMINDER: Informatics Colloquium Mo 17.07.17 at 17:15 in D-125 with Prof. Dr. Andreas Holzinger/ Medical University Graz

Dear all,
May we kindly remind you of the 
today's talk at 17:15 in room D-125. Please find the details below.
Best regards
Stephanie Schulte Hemming
 

Von: Schulte Hemming, Stephanie
Gesendet: Dienstag, 4. Juli 2017 13:14
An: kolloquium@informatik.uni-hamburg.de
Betreff: INVITATION: Informatics Colloquium Mo 17.07.17 at 17:15 in D-125 with Prof. Dr. Andreas Holzinger/ Medical University Graz

This is an invitation to the next Informatics Colloquium on Monday, 17 July 2017, 17:15, Campus "Informatikum/Stellingen", Room D-125. The talk entitled "Machine Learning and Knowledge Extraction: The challenge is in small amount of data sets" will be held by Prof. Dr. Andreas Holzinger, Professor at Medical University Graz, Institute for Medical Informatics/Statistics.

                

This talk will be held in English. The colloquium committee is looking forward to seeing you all there and to sharing this talk with you. For details on the series of colloquiums planned, please visit  https://www.inf.uni-hamburg.de/home/kolloquium/sose17.html

 

On behalf of the colloquium committee

Stephanie Schulte Hemming

Universität Hamburg

 

 

ABSTRACT:

The goal of Machine Learning is to learn from data, to extract and discover knowledge, and to help to make decisions under uncertainty. In automatic machine learning (aML) great advances have been made, for example, in speech recognition, recommender systems, or autonomous vehicles. Automatic approaches greatly benefit from "big data" with many training sets. However, sometimes we are confronted with a small amount of complex data sets, where aML suffers of insufficient training samples. The application of such aML approaches in complex application domains, e.g. as in health informatics seems elusive in the near future, and a good example are Gaussian processes, where aML (e.g. standard kernel machines) struggle on function extrapolation problems, which are trivial for human learners. In such situations, interactive Machine Learning (iML) can be beneficial where a human-in-the-loop helps in solving computationally hard problems, e.g., subspace clustering, protein folding, or k-anonymization of health data, where the knowledge and experience of human experts can help to reduce an exponential search space through heuristic selection of samples. Therefore, what would otherwise be an NP-hard problem reduces greatly in complexity through the input and the assistance of an human agent involved directly into the learning phase. Tackling such challenges needs a concerted effort, fostering integrative ML research between experts ranging from diverse disciplines, from data science to visualization, and both disciplinary excellence and a cross-disciplinary skill-set with international collaboration.

 

BIO:

Andreas Holzinger is lead of the Holzinger Group HCI–KDD, Institute for Medical Informatics/Statistics at the Medical University Graz, and Associate Professor of Applied Computer Science at the Faculty of Computer Science and Biomedical Engineering at Graz University of Technology. Currently, Andreas is Visiting Professor for Machine Learning in Health Informatics at the Faculty of Informatics at Vienna University of Technology. He serves as consultant for the Canadian, US, UK, Swiss, French, Italian and Dutch governments, for the German Excellence Initiative, and as national expert in the European Commission. Andreas obtained a PhD in Cognitive Science from Graz University in 1998 and his Habilitation (second PhD) in Computer Science from Graz University of Technology in 2003. Andreas was Visiting Professor in Berlin, Innsbruck, London (twice), Aachen, and Verona. Andreas and his Group work on extracting knowledge from data and foster a synergistic combination of methodologies of two areas that offer ideal conditions towards unraveling problems with complex health data: Human-Computer Interaction (HCI) and Knowledge Discovery/Data Mining (KDD), with the central goal of supporting human intelligence with machine learning to discover novel, previously unknown insights into data. To stimulate crazy ideas at international level without boundaries, Andreas founded the international Expert Network HCI–KDD. Andreas is Associate Editor of Knowledge and Information Systems (KAIS), Associate Editor of Springer Brain Informatics (BRIN) and Section Editor for Machine Learning of BMC Medical Informatics and Decision Making (MIDM). He is member of IFIP WG 12.9 Computational Intelligence, the ACM, IEEE, GI and the Austrian Computer Society. Home: http://hci-kdd.org

  

CONTACT:

Prof. Dr. Chris Biemann, Universität Hamburg, FB Informatik