UPC TelecomBCN organises two open lectures as a conclusion of the 3rd Summer School on Deep Learning for Computer Vision. Two renowned researchers with a high international impact will present their latest research on deep learning applied to computer vision. The two lectures will be preluded by student project presentations and a poster session of research papers from local scientists, also open to the public.

Schedule

10:00 Laura Leal-Taixé (Technical University of Munich - TUM)

10:40 Kevin McGuinness (Dublin City University - DCU)

11:30 Poster Session: Research Papers (submit your published work here).

12:30 Oral Session: Student Projects

13:20 Award, closing and course offer at UPC.

You are invited to prepare these sessions beforehand with the course material available online from Introduction to Deep Learning, Deep Learning for Artificial Intelligence and Deep Learning for Computer Vision.

The organisers may limit the access to the room to ticket holders only.

Short bios

Laura Leal-Taixé (Technical University of Munich - TUM)

Dr. Laura Leal-Taixé (b. 1984) conducts research in the area of Computer Vision and Machine Learning. In particular, she focuses on video analysis, solving tasks such as multiple object tracking, motion analysis or semantic segmentation. Allowing machines to automatically analyse video data is essential for applications such as Autonomous Driving. Dr. Laura Leal-Taixé was born in Barcelona where she pursued B.Sc. and M.Sc. in Telecommunications Engineering at the Technical University of Catalonia (UPC). She went to Boston, USA to do her Masters Thesis at Northeastern University with a fellowship from the Vodafone foundation. From 2009 until 2013, she worked towards her PhD degree at the Institute for Information Processing (TNT) of the Leibniz University of Hannover in Germany. During her PhD, she was at the University of Michigan, Ann Arbor, USA for one year as a visiting scholar with Prof. Silvio Savarese. She ithen spent two years as a postdoctoral researcher at the Institute for Geodesy and Photogrammetry at ETH Zürich, Switzerland, working on tracking and benchmarking. In May 2016, she moved to Munich where she started working at the Computer Vision Group as a senior postdoctoral researcher. She is currently a junior group leader after receiving a Sofja Kovalevskaja Award of 1.65 million euros for her project socialMaps.

Kevin McGuinness (Dublin City University)

Dr Kevin McGuinness is an Assistant Professor and Science Foundation Ireland Funded Starting Investigator with the School of Electronic Engineering in Dublin City University. He also works very closely with the Insight Centre for Data Analytics. He finished my B.Sc (Hons) in Computer Applications and Software Engineering in Dublin City University in 2005 and was awarded a Ph.D. from the School of Electronic Engineering in 2009. He has since been a postdoctoral researcher at the CLARITY Centre for Sensor Web Technologies, and a research fellow at the Insight Centre for Data Analytics. His primary research interests are computer vision, deep learning, image and video segmentation, segmentation evaluation, machine learning, content-based multimedia information retrieval, and human-computer interaction.

Talk - Crowd counting and analysis: Understanding images containing medium to large groups of people is becoming an increasingly important application of computer vision. Stadiums, airports, concerts, and cities, routinely facilitate large crowds and need to handle the corresponding safety and logistical issues that arise. Crowded images bring their own particular challenges and many approaches have been proposed for counting, density estimation, behaviour classification, and anomaly detection. This talk will focus on our recent work in Insight/DCU on crowded scene analysis and on how we use deep learning, multi-task learning, and domain adaptation for counting and analysing crowds. I will also describe our 2018 CVPR paper that describes how counting models can be adapted across domains, which allows counting of penguins, cells, cars, and people using a model with 95% shared parameters.

Accepted Posters

• #01 Yaxing Wang (CVC-UAB), “Mix and match networks: encoder-decoder alignment for zero-pair image translation”. CVPR 2018.

• #02 Xialei Liu (CVC-UAB), “Leveraging Unlabeled Data for Crowd Counting by Learning to Rank”. CVPR 2018.

• #03 Víctor Campos (BSC-UPC), “Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks”. ICLR 2018.

• #04 Xavier Giro-i-Nieto (UPC), “Recurrent Neural Networks for Semantic Instance Segmentation”. CVPR 2018 DeepVision Workshop.

• #05 Andreu Girbau (NII Tokyo), “Tracked Instance Search”. ICASSP 2018.

• #06 Carlos Roig (Vilynx), “Unsupervised Large-Scale World Locations Dataset”. CVPR 2018 Webvision Workshop.

• #07 Eva Mohedano (Insight DCU), “Deep Image Representations for Instance Search”. Under review.