Invited speakers

Cees Snoek is a full professor in computer science at the University of Amsterdam, where he heads the Video & Image Sense lab. He is also a director of three public-private AI-research labs: QUVA lab with Qualcomm, Atlas lab with TomTom and AIM lab with the Inception Institute of Artificial Intelligence. At University spin-off Kepler Vision Technologies he acts as Chief Scientific Officer. He is also the director of the master program in Artificial Intelligence and co-founder of the Netherlands Innovation Center for Artificial Intelligence. He was previously visiting scientist at Carnegie Mellon University and UC Berkeley, head of R&D at University spin-off Euvision Technologies and managing principal engineer at Qualcomm Research Europe. His research interests focus on making sense of video and images. He has published over 200 refereed journal and conference papers, serves on the editorial board of IEEE Transactions on Pattern Analysis and Machine Intelligence and frequently serves as an area chair of the major conferences in computer vision and multimedia. Professor Snoek was the lead researcher of the award-winning MediaMill Semantic Video Search Engine, which was the most consistent top performer in the yearly NIST TRECVID evaluations for over a decade. He was general chair of ACM Multimedia 2016 in Amsterdam and initiator of the VideOlympics. Cees is recipient of an NWO Veni career award, a Fulbright Junior Scholarship, an NWO Vidi career award, and the Netherlands Prize for ICT Research. Together with his Ph.D. students and Post-docs he has won several best paper awards.

Progress in video understanding has been astonishing in the past decade. Classifying actions, tracking objects and even segmenting actor instances at the pixel level is now common place, thanks to data-and-label supervised deep learning. Yet, it is becoming increasingly clear that deep learning architectures for video understanding may perform well on academic datasets constrained on domain diversity, recording circumstances and label vocabulary, but have difficulty generalizing to video in an open world where sensory, spatiotemporal and semantic conditions will differ considerably from those perceived during training. In this talk I will present recent work from my lab that strives for real-world video understanding by 1) leveraging sound, in addition to sight, in challenging vision conditions, 2) localizing previously unseen activities in space and time from a few video examples without class labels, interval bounds, or bounding boxes, and 3) recognizing and localizing previously unseen actions without any examples, by relying on off-the-shelf object detectors and multi-lingual word embeddings. Our experiments demonstrate state-of-the-art ability in the traditional closed world setting, while enabling video recognition and retrieval in an open world.

Prof. Pavel Zezula is a professor of Informatics at the Masaryk University, Brno, Czech Republic specializing in research and education in management of data. He spent more than ten years in Italy, cooperating with the Italian National Research Council in Pisa and the University of Bologna. He is co-author of the Similarity Search: The Metric Space Approach book, published by Springer US. He has published more than 120 peer reviewed conference and 40 journal papers with the total count acceding in Scholar Google 7100 citations – he has supervised over 20 PhD students. He participated in more than 20 European projects and received the IBM SUR award for his activities in the “Web Search Similarity Search in Multimedia Data”. Currently is Prof Zezula heading at Masaryk University the DISA (Data Intensive Systems and Applications) laboratory, concentrating on research in Large-Scale Multimodal Data Interpretation. He is a steering committee member of SISAP (Similarity Search and Applications) series of international conferences.

As the current data is weakly structured or unstructured at all, access to objects is only possible through similarity of the object’s salient features or properties. Consequently, similarity approach to searching is increasingly playing more and more important role in development of data processing applications. In the last twenty years, the technology has matured and many centralized, distributed, and even peer-to-peer architectures have been proposed. However, the use of similarity searching in numerous potential applications is still a challenge. In the talk, four research directions in developing similarity search applications at Masaryk University DISA laboratory are to be discussed. First, we concentrate on accelerating large-scale face recognition applications and continue with generic image annotation task for retrieval purposes. In the second half, we focus on data stream processing applications and finish the talk with an ambition topic of content-based retrieval in human motion-capture data. Applications will be illustrated by online prototype implementations.

Jiri Matas is a full professor at the Center for Machine Perception,
Czech Technical University in Prague. He holds a PhD degree from the University of Surrey, UK (1995). He has published more than 250 papers in refereed journals and conferences. His publications have about 50000 citations registered in Google Scholar and 20000 in the Web of Science. His h-index is 80 (Google scholar) and 54 (Clarivate Analytics Web of Science) respectively.

He received the best paper prize e.g. at the British Machine Vision Conferences in 2002 and 2005, at the Asian Conference on Computer Vision in 2007 and at Int. Conf. on Document analysis and Recognition in 2015. J. Matas has served in various roles at major international computer vision conferences (e.g. ICCV, CVPR, ICPR, NIPS, ECCV), co-chairing ECCV 2004, 2016, 2022 and CVPR 2007 and 2022. He is an Editor-in-Chief of IJCV and was an Associate Editor-in-Chief of IEEE T. PAMI. He served on the computer science panel of ERC.

His research interests include visual tracking, object recognition, image matching and retrieval, sequential pattern recognition, and RANSAC- type optimization methods. He has co-founded two companies, Eyedea Recognition (computer vision) and Locksley (combinatorial optimization).

The talk will cover recent developments and the state-of-the-art of image-based recognition applied to plants, fungi and animals. Despite being close to standard image classification, the problem of visual recognition of natural object has specific characteristics, such as availability of information about time, location and the environment which we show can be exploited to improve accuracy. The domain attracts the interest of volunteers and experts and a huge amount of constantily growing labelled public data is available, making it an interesting field for testing deep learning algorithms on fine-grained classification of long-tail data. The deployment of the presented methods will be discussed too.