Crowdsourcing
Many applications require input that can hardly be provided automatically, since the task is too complex for computers, but rather trivial for human beings. At the same time, the scale of these problems does not allow the task to be solved by dedicated experts; rather, the wisdom of the crowd is leveraged for data annotation, classification, or even data capturing. Managing the data that is provided by such crowdsourcing applications and guaranteeing a high degree of data quality (e.g., automatic disambiguation and integration into a coherent data set) is crucial.
Work at the DBIS group addresses the following applications:
- Citizens' Observatories: While various dedicated sensors for a broad range of environmental parameters exist, usually together with specialized applications for automated data analysis, there are still many environmental phenomena that cannot be easily captured. An example is soil degradation and erosion. In other cases, even though sophisticated sensors exist, the sensor information can hardly be processed automatically, especially when is consists of or includes images, 3D models, etc. Examples are invasive alien species which can only be identified with the help of professional or lay taxonomists. In our work, we have devised a smartphone app (COSA: Citizens' Observatories Smartphone App) in collaboration with experts from the environmental sciences that supports the crowdsourcing of data capturing and/or data analysis in the environmental sciences.
- Crowdsourced event detection and annotation in videos: The wisdom of the crowd is used to create metadata annotations to videos. We have used the contribution of crowd workers to annotate sports videos (e.g., in a soccer video: which player is in possession of the ball, on which part of the filed, etc.). These annotations then allow to support novel retrieval applications, called SportSense.
- Querying crowdsourced multimedia data: Crowdsourcing multimedia content (e.g., images and videos of places of interest in tourist applications) leads to big but also heterogeneous collections. In our work, we aim at providing a large variety of query paradigms on top of crowdsourced and/or curated content, and support a range of different devices for accessing hese data.
Staff
Research Projects
- Citizens’ Observatories
- City-Stories: Spatio-temporal search over crowdsourced content
- Participatory Knowledge Practices in Analogue and Digital Image Archives
- SportSense - Sketch-based spatio-temporal Query Support for Sports Videos
- verifir - Real-time Detection and Analysis of Disinformation on the Web
- WeObserve: Integrating Citizen Observers and High Throughput Sensing Devices for Big Data Collection, Integration, and Analysis
Thesis Projects
- Bachelor/Master Theses in Data Integration
- Data Integration for Bird Migration Monitoring
- Development of a Platform for the Provision of Location-based Multimedia Documents
- Enriching Cultural Heritage Metadata through Gamified Crowdsourcing
- GoFind! Augmented Reality
- Linked Open Data Integration for GoFind!
Publications
2024
- Loris Sauter
Flexible Information Retrieval Evaluation
PhD Thesis, Department of Mathematics and Computer Science, University of Basel, Switzerland, 2024/2 - Loris Sauter, Tim Bachmann, Heiko Schuldt, Luca Rossetto
Augmented Reality Photo Presentation and Content-Based Image Retrieval on Mobile Devices with AR-Explorer
Proceedings of the 30th International Conference on Multimedia Modeling (MMM 2024), Amsterdam, Netherlands, 2024/1
2023
- Loris Sauter, Tim Bachmann, Luca Rossetto, Heiko Schuldt
Spatially Localised Immersive Contemporary and Historic Photo Presentation on Mobile Devices in Augmented Reality
Proceedings of the 5th Workshop on analySis, Unerstanding and proMotion of heritAge Contents, Ottowa ON, Canada, 2023/11 - Shaban Shabani
Hybrid Human-Machine Information Systems for Data Classification
PhD Thesis, Department of Mathematics and Computer Science, University of Basel, Switzerland, 2023/6 - Murielle Cornut, Julien Antoine Raemy, Florian Spiess
Annotations as Knowledge Practices in Image Archives: Application of Linked Open Usable Data and Machine Learning
ACM Journal on Computing and Cultural Heritage, 2023/5
2022
- Simon Peterhans, Loris Sauter, Florian Spiess, Heiko Schuldt
Automatic Generation of Coherent Image Galleries in Virtual Reality
Proceedings of the 26th International Conference on Theory and Practice of Digital Libraries (TPDL ‘22), Padua, Italy, 2022/9
2021
- Philipp Seidenschwarz
Data-Driven Analytics for Decision Making in Game Sports
PhD Thesis, Department of Mathematics and Computer Science, University of Basel, Switzerland, 2021/9 - Laura Rettig, Shaban Shabani, Loris Sauter, Philippe Cudré-Mauroux, Maria Sokhn, Heiko Schuldt
City-Stories: Combining Entity Linking, Multimedia Retrieval, and Crowdsourcing to Make Historical Data Accessible
Proceedings of the 21st International Conference on Web Engineering (ICWE 2021), Biarritz, France (held virtually), 2021/5 - Ralph Gasser, Luca Rossetto, Silvan Heller, Heiko Schuldt
Multimedia Retrieval and Analysis with Cottontail DB
ACM SIGMM Records, 2021/3 - Shaban Shabani, Zarina Charlesworth, Maria Sokhn, Heiko Schuldt
SAMS: Human-in-the-loop Approach to Combat the Sharing of Digital Misinformation
Proceedings of the AAAI 2021 Spring Symposium on Combining Machine Learning and Knowledge Engineering (AAAI-MAKE 2021), Stanford University, Palo Alto, California, USA (held virtually), 2021/3
2020
- Lukas Probst, Heiko Schuldt, Philipp Seidenschwarz, Martin Rumo
StreamTeam-Football: Analyzing Football Matches in Real-Time on the Basis of Position Streams
Proceedings of the IEEE International Conference on Big Data (BigData 2020) , Atlanta, GA, USA (held virtually), 2020/12 - Ralph Gasser, Luca Rossetto, Silvan Heller, Heiko Schuldt
Cottontail DB: An Open Source Database System for Multimedia Retrieval and Analysis
Proceedings of 28th ACM International Conference on Multimedia.(ACM MM 2020) - Open Source Competition, Seattle, WA, USA (held virtually), 2020/10 - Philipp Seidenschwarz, Martin Rumo, Lukas Probst, Heiko Schuldt
High-Level Tactical Performance Analysis with SportSense
Proceedings of the 3rd International ACM Workshop on Multimedia Content Analysis in Sports (MMSports 2020), Seattle, WA, USA (held virtually), 2020/10 - Shaban Shabani, Maria Sokhn, Heiko Schuldt
Hybrid Human-Machine Classification System for Cultural Heritage Data
Proceedings of the 2nd workshop on Structuring and Understanding of Multimedia heritAge Contents (SUMAC 20), Seattle, WA, USA (held virtually), 2020/10 - Ihab Al Kabary, Heiko Schuldt
Scalable Sketch-based Sport Video Retrieval in the Cloud
Proceedings of the International Conference on Cloud Computing (CLOUD’20), Honolulu, Hi, USA (held virtually), 2020/9 - Philipp Seidenschwarz, Adalsteinn Jonsson, Michael Plüss, Martin Rumo, Lukas Probst, Heiko Schuldt
The SportSense User Interface for Holistic Tactical Performance Analysis in Football
Proceedings of the 25th International Conference on Intelligent User Interfaces Companion (IUI 2020 Companion), Cagliari, Italy (held virtually), 2020/3
2019
- Philipp Seidenschwarz, Adalsteinn Jonsson, Fabian Rauschenbach, Martin Rumo, Lukas Probst, Heiko Schuldt
Combining Qualitative and Quantitative Analysis in Football with SportSense
Proceedings of the 2nd International ACM Workshop on Multimedia Content Analysis in Sports (MMSports 2019), Nice, France, 2019/10 - Ivan Giangreco, Loris Sauter, Mahnaz Amiri Parian, Ralph Gasser, Silvan Heller, Luca Rossetto, Heiko Schuldt
VIRTUE — A Virtual Reality Museum Experience
Proceedings of the 24th ACM International Conference on Intelligent User Interfaces (IUI’19), Los Angeles, CA, USA, 2019/3
2018
- Loris Sauter, Luca Rossetto, Heiko Schuldt
Exploring Cultural Heritage in Augmented Reality with GoFind!
Proceedings of the first IEEE International Conference on Artificial Intelligence and Virtual Reality, Taichung, Taiwan, 2018/12 - Lukas Probst, Fabian Rauschenbach, Heiko Schuldt, Philipp Seidenschwarz, Martin Rumo
Integrated Real-Time Data Stream Analysis and Sketch-Based Video Retrieval in Team Sports
Proceedings of the 2018 IEEE International Conference on Big Data (BigData 2018), Seattle, WA, USA, 2018/12 - Silvan Heller, Luca Rossetto, Heiko Schuldt
The PS-Battles Dataset - an Image Collection for Image Manipulation Detection
arXiv cs.MM, 2018/4 - Lukas Probst, Ihab Al Kabary, Rufus Lobo, Fabian Rauschenbach, Heiko Schuldt, Philipp Seidenschwarz, Martin Rumo
SportSense: User Interface for Sketch-Based Spatio-Temporal Team Sports Video Scene Retrieval
Proceedings of the IUI 2018 Workshop on User Interfaces for Spatial and Temporal Data Analysis (UISTDA 2018), Tokyo, Japan, 2018/3
2017
- Shaban Shabani, Maria Sokhn, Laura Rettig, Philippe Cudré-Mauroux, Lukas Beck, Claudiu Tănase, Heiko Schuldt
City-Stories: A Multimedia Hybrid Content and Entity Retrieval System for Historical Data
Proceedings of the 4th International Workshop on Computational History (HistoInformatics 2017), Singapore, 2017/11
2016
- Lukas Beck, Heiko Schuldt
City-Stories: A Spatio-Temporal Mobile Multimedia Search System
Proceedings of the 2016 IEEE International Symposium on Multimedia (ISM 2016), San Jose, CA, USA, 2016/12
2015
- Christine Alewell, Katrin Meusburger, Daniela Kandl, Ilir Fetai, Volker Roth, Valentino Rugolo, Heiko Schuldt und Thomas Vetter
COSA – AlpErosion: Monitoring the degradation of Alpine soils with COSA, a Citizens’ Observatory Smartphone App
Bulletin der Bodenkundlichen Gesellschaft der Schweiz, 2015/2
2014
- Fabio Sulser, Ivan Giangreco, Heiko Schuldt
Crowd-based Semantic Event Detection and Video Annotation for Sports Videos
Proceedings of the International ACM Workshop on Crowdsourcing for Multimedia (CrowdMM), Orlando, FL, USA, 2014/11 - Ihab Al Kabary, Heiko Schuldt
Enhancing Sketch-based Sport Video Retrieval by Suggesting Relevant Motion Paths
Proceedings of the 37th ACM SIGIR Conference, Gold Coast, Australia, 2014/7 - Ihab Al Kabary, Heiko Schuldt
Using Hand Gestures for Specifying Motion Path Queries in Sketch-based Video Retrieval
Proceedings of the 36th European Conference on Information Retrieval (ECIR), Amsterdam, Netherlands, 2014/4
2013
- Ihab Al Kabary, Heiko Schuldt
Towards Sketch-based Motion Queries in Sports Videos
Proceedings of the 15th IEEE International Symposium on Multimedia (ISM 2013), Anaheim, CA, USA, 2013/12 - Ihab Al Kabary, Heiko Schuldt
SportSense: Using Motion Queries to Find Scenes in Sports Videos
Proceedings of the 22nd ACM International Conference on Information and Knowledge Management (CIKM 2013), San Francisco, CA, USA, 2013/10