Important Dates

  • Deadline for extended abstract submissions: 25th of July 2018
  • Acceptance notification: 1st of August 2018
  • Workshop: 14th of September 2018

Keynote Speakers

  • Kristen Grauman (UT Austin, United States)
    Kristen Grauman is a Professor in the Department of Computer Science at the University of Texas at Austin. Her research in computer vision and machine learning focuses on visual recognition and search. Before joining UT-Austin in 2007, she received her Ph.D. at MIT. She is an Alfred P. Sloan Research Fellow and Microsoft Research New Faculty Fellow, a recipient of NSF CAREER and ONR Young Investigator awards, the Regents' Outstanding Teaching Award from the University of Texas System in 2012, the PAMI Young Researcher Award in 2013, the 2013 Computers and Thought Award from the International Joint Conference on Artificial Intelligence (IJCAI), the Presidential Early Career Award for Scientists and Engineers (PECASE) in 2013, and the Helmholtz Prize in 2017. She was inducted into the UT Academy of Distinguished Teachers in 2017. She and her collaborators were recognized with the CVPR Best Student Paper Award in 2008 for their work on hashing algorithms for large-scale image retrieval, the Marr Prize at ICCV in 2011 for their work on modeling relative visual attributes, the ACCV Best Application Paper Award in 2016 for their work on automatic cinematography for 360 degree video, and a Best Paper Honorable Mention at CHI in 2017 for work on crowds and visual question answering. She currently serves as an Associate Editor in Chief for the Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and as an Editorial Board member for the International Journal of Computer Vision (IJCV). She also served/serves as a Program Chair of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015 and a Program Chair of Neural Information Processing Systems (NIPS) 2018.
  • Christoph Lampert (IST Austria)
    Christoph Lampert received the PhD degree in mathematics from the University of Bonn in 2003. In 2010 he joined the Institute of Science and Technology Austria (IST Austria) first as an Assistant Professor and since 2015 as a Professor. His research on computer vision and machine learning has won several international and national awards, including the best paper prize at CVPR 2008. In 2012 he was awarded an ERC Starting Grant by the European Research Council. He currently is an Editor of the International Journal of Computer Vision (IJCV), Action Editor of the Journal for Machine Learning Research (JMLR), and Associate Editor in Chief of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
  • Joachim Denzler (University of Jena, Germany)
    Joachim Denzler earned the degrees “DiplomInformatiker”, “Dr.-Ing.” and “Habilitation” from the University of Erlangen, Germany, in years 1992, 1997, and 2003, respectively. Currently, he holds a position as full professor for computer science and is head of the Computer Vision Group at the Friedrich Schiller University Jena, Germany. He is also Director of the Michael Stifel Center for Data-Driven and Simulation Science, Jena. His research interests comprise the automatic analysis, fusion, and understanding of sensor data, especially development of methods for visual recognition tasks and dynamic scene analysis. He contributed in the area of active vision, 3D reconstruction, as well as object recognition and tracking. He is author and co-author of over 300 journal and conference papers as well as technical articles. He is a member of IEEE, IEEE computer society, DAGM, and GI.
  • Jordi Pont-Tuset (Google AI, Switzerland)
    Jordi Pont-Tuset is a research scientist at Google AI, Switzerland, since January 2018. Previously, he was a post-doctoral researcher at ETHZ, Switzerland, in Prof. Luc Van Gool’s Computer Vision Lab since 2015; and interned in Disney Research, Zürich, with Prof. Aljoscha Smolic in 2014. During his PhD, he collaborated with Prof. Jitendra Malik’s vision group in UC Berkeley (2013). He received his Ph.D with honors in 2014, the M.Sc. in Research on Information and Communication Technologies in 2010, the degree in Mathematics in 2008, and the degree in Electrical Engineering in 2008; all from the Universitat Politècnica de Catalunya, BarcelonaTech (UPC).
  • Tinne Tuytelaars (KU Leuven, Belgium)
    Tinne Tuytelaars is a professor at KU Leuven Belgium. She received a Master’s degree in electrical engineering and PhD degree from the KU Leuven, Belgium in 1996 and 2000. Her research interests are object recognition, action recognition, multimodal analysis, and image representations. She received the Koenderink Award at ECCV in 2016 for fundamental contributions in computer vision that stood the test of time as well as the CVIU Most Cited Paper Award 2011 and an ERC Starting Grant in 2009. She serves as an Associate Editor in Chief of TPAMI, a member of the Editorial Board of CVIU and has been one of the program chairs for ECCV 2014 and one of the general chairs of CVPR 2016.

Program

09:00am - 09:10am
Welcome and Introduction
09:10am - 09:40am
Tinne Tuytelaars (KU Leuven) - "Incremental learning: a critical view on the current state of affairs"
09:45am - 10:15am
Manuel Günther - “Results and Evaluation of the Open-Face Challenge” (challenge website)
10:15am - 10:45am
Coffee Break
10:45am - 11:15am
Kristen Grauman (UT Austin) - “Recognition with unseen compositions and novel environments“
11:20am - 11:50am
Jordi Pont-Tuset (Google AI) - “Interactive video segmentation: The DAVIS benchmark and first approaches”
11:50am - 12:30am
Posters
12:30am - 02:00pm
Lunch Break
02:00pm - 02:30pm
Christoph Lampert (IST Austria) - "Towards continual learning and interactive annotation"
02:35pm - 03:05pm
Joachim Denzler (Univ. Jena) - “Elements of Continuous Learning for Wildlife Monitoring“
03:05pm
Workshop Closing

Accepted Posters

The following posters will be presented during the workshop:
Lawrence Neal, Matthew Olson, Xiaoli Fern, Weng-Keen Wong, Fuxin Li Open Set Learning with Counterfactual Images
Manuel Guenther, Walter Scheirer, Terry Boult Open-Set Recognition Challenge
Pau Panareda Busto and Juergen Gall Open Set Domain Adaptation for Image and Action Recognition
Kshitij Dwivedi and Gemma Roig Evaluation of plug and play modules for multi-domain learning
SouYoung Jin and Aruni RoyChowdhury and Huaizu Jiang and Ashish Singh and Aditya Prasad and Deep Chakraborty and Erik Learned-Miller Unsupervised Hard Example Mining from Videos for Improved Object Detection
Aljosa Osep and Paul Voigtlaender and Jonathon Luiten and Stefan Breuers and Bastian Leibe Towards Large-Scale Video Object Mining
Lisa Wang and Ranti Dev Sharma Unsupervised Representation Learning on Multispectral Imagery By Predicting Held-Out Bands
Ranti Dev Sharma and Lisa Wang Human-in-the-loop segmentation for improved segmentation and annotations
Hartmut Bauermeister and Peter Ochs and Tim Meinhardt and Laura Leal-Taixe and Michael Moeller Adaptive Network Architectures via Linear Splines
Kate Rakelly* and Evan Shelhamer* and Trevor Darrell and Alexei A. Efros and Sergey Levine Few-Shot Segmentation Propagation with Guided Networks

Call for Abstracts and Participation

Learning algorithms are the backbone of computer vision research and still focused on training from large amounts of already annotated data. The limitations we are currently observing in many applications are mostly due to the lack of annotations or changing data distributions over time. To overcome these barriers, the annotation and learning of models needs to be coupled strongly through human-machine interaction. Furthermore, models need to adapt as needed to handle either shifts or completely novel data. The goal of this workshop is to discuss and present the advances in technologies that support annotation, model learning through expert guidance and continuous model adaptation.

  • Online and incremental learning
  • Interactive segmentation and detection to support annotation
  • Transfer learning
  • Active or self-taught
  • Continuous / lifelong learning
  • Open set learning
  • Open domain learning
  • Efficient fine-tuning of generic models
  • Personalization and customization
  • Privacy-preserving learning

We invite abstract submissions of 4-pages in general following the ECCV18/Springer format.

Deadline: 25th of July 2018
Submission: Google form

The abstract will not appear in any proceedings and if accepted only appear online on this page (if authors like). Our workshop is not meant as a publication venue, but rather a real meeting, where you learn about people interested in the same area and find the next cooperation partners for your future project.

Accepted abstracts will be presented in a quick teaser or poster. We also welcome submissions of industrial partners interested in the topic and willing to present their application area. Furthermore, if you want to present your next proposal idea and you are looking for cooperation partners, you are also very much invited to submit an abstract.