A5101788615- Advanced Graph Neural Networks
- Multimodal Machine Learning Applications
- Topic Modeling
- Data Quality and Management
- Video Analysis and Summarization
- Advanced Image and Video Retrieval Techniques
- Human Pose and Action Recognition
- Data Mining Algorithms and Applications
- Domain Adaptation and Few-Shot Learning
- Biomedical Text Mining and Ontologies
- Context-Aware Activity Recognition Systems
- Reinforcement Learning in Robotics
- Semantic Web and Ontologies
- Adaptive Dynamic Programming Control
- Neural Networks and Reservoir Computing
University of Zurich
2014-2022
The data produced by efforts such as life logging is commonly multi modal and can have manifold interrelations with itself well external information. Representing this in a way that these rich relations all the different sources be leveraged non-trivial undertaking. In paper, we present first iteration of LifeGraph, Knowledge Graph for lifelogging data. LifeGraph aims at not only capturing aspects contained lifelog but also linking them to external, static knowledge bases order put log whole...
The multi-modal and interrelated nature of lifelog data makes it well suited for graph-based representations. In this paper, we present the second iteration LifeGraph, a Knowledge Graph Lifelog Data, initially introduced during 3rd Search Challenge in 2020. This incorporates several lessons learned from previous version. While actual graph has undergone only small changes, mechanisms by which is traversed querying as underlying storage system performs traversal have been changed. means query...
The Semantic Web is distributed yet interoperable: Distributed since resources are created and published by a variety of producers, tailored to their specific needs knowledge; Interoperable as entities linked across resources, allowing use from different providers in concord. Complementary the explicit usage embedding methods made them applicable machine learning tasks. Subsequently, models for numerous tasks structures have been developed, spaces various published. ecosystem but not Entity...
While a multitude of approaches for extracting semantic information from multimedia documents has emerged in recent years, isolating any form holistic representation larger type document, such as movie, is not yet feasible. In this paper we present our used the first instance Deep Video Understanding Challenge, using combination several multi-modal detectors and an integration scheme informed by methods web context order to determine capabilities limitations currently available extraction...
In recent years, several studies proposed the application of echo state networks (ESN) to adaptive reinforcement learning schemes for control artificial autonomous agents. Especially actor-critic design (ACD) is a promising candidate robotic systems with continuous and action spaces, as was demonstrated in using simple wheeled robots. present work, we investigate applicability this framework more complex systems, namely quadruped running robot rich dynamics. New challenges questions arise,...
Knowledge Graphs (KGs) have become increasingly popular in the recent years. However, as knowledge constantly grows and changes, it is inevitable to extend existing KGs with entities that emerged or became relevant scope of KG after its creation. Research on updating typically relies extracting named relations from text. these approaches cannot infer were not explicitly stated. Alternatively, embedding models exploit implicit structural regularities predict missing relations, but entities....