Project Lab Human Activity Understanding
| Lecturer (assistant) | |
|---|---|
| Number | 0000000155 |
| Type | practical training |
| Duration | 5 SWS |
| Term | Winter semester 2026/27 |
| Language of instruction | English |
| Position within curricula | See TUMonline |
| Dates | See TUMonline |
- 15.10.2026 13:15-17:15 0943, Praktikum
- 22.10.2026 13:15-17:15 0943, Praktikum
- 29.10.2026 13:15-17:15 0943, Praktikum
- 05.11.2026 13:15-17:15 0943, Praktikum
- 12.11.2026 13:15-17:15 0943, Praktikum
- 19.11.2026 13:15-17:15 0943, Praktikum
- 26.11.2026 13:15-17:15 0943, Praktikum
- 10.12.2026 13:15-17:15 0943, Praktikum
- 17.12.2026 13:15-17:15 0943, Praktikum
- 07.01.2027 13:15-17:15 0943, Praktikum
- 14.01.2027 13:15-17:15 0943, Praktikum
- 21.01.2027 13:15-17:15 0943, Praktikum
- 28.01.2027 13:15-17:15 0943, Praktikum
- 04.02.2027 13:15-17:15 0943, Praktikum
Admission information
Description
Sensor data collection and annotation
- Multi-sensor and multi-view data collection and processing, including color/depth/IMU
- Synthetic data generation for Human Actions
- Accelerated ground truth annotation using interactive instance segmentation and tracking
Semantic inference building blocks
- Object detection
- Human and Object pose estimation/tracking
Graph representation of spatial and temporal data
- 3D scene graphs
- Spatio-Temporal graphs
- Knowledge Bases (Ontologies)
Sequential deep learning models for Human Activity Recognition and Anticipation
- Recurrent Neural Networks
- Graph Networks
- Transformers
- Multi-sensor and multi-view data collection and processing, including color/depth/IMU
- Synthetic data generation for Human Actions
- Accelerated ground truth annotation using interactive instance segmentation and tracking
Semantic inference building blocks
- Object detection
- Human and Object pose estimation/tracking
Graph representation of spatial and temporal data
- 3D scene graphs
- Spatio-Temporal graphs
- Knowledge Bases (Ontologies)
Sequential deep learning models for Human Activity Recognition and Anticipation
- Recurrent Neural Networks
- Graph Networks
- Transformers
Teaching and learning methods
- Supervised weekly lab sessions with several introductory lectures by research assistants at the beginning of the
course and supervised practical implementation based on the provided skeleton codes.
- Individual methods and solutions introduced by the student
- Lectures on theoretical basics of project planning and technical management. and tools for collaboration (SCRUM, Gitlab, Wiki, etc.)
- Final project: individual and group work with independent planning, execution, and documentation
- Seminar: Presentation and final results and discussion (reflection, feedback).
Media formats:
The following media forms will be used:
- Presentations
- Script and review articles from the technical literature
- Tutorials and software documentation
- Development Environment (virtual machines on a GPU server)
- Simulation environment
- Data collection setup
course and supervised practical implementation based on the provided skeleton codes.
- Individual methods and solutions introduced by the student
- Lectures on theoretical basics of project planning and technical management. and tools for collaboration (SCRUM, Gitlab, Wiki, etc.)
- Final project: individual and group work with independent planning, execution, and documentation
- Seminar: Presentation and final results and discussion (reflection, feedback).
Media formats:
The following media forms will be used:
- Presentations
- Script and review articles from the technical literature
- Tutorials and software documentation
- Development Environment (virtual machines on a GPU server)
- Simulation environment
- Data collection setup
Links
Previous Lab Project Demos
SoSe22
Kick off meeting announcement
The lab kick-off meeting will be in-person on 15.10.2026 in Room 0943, Praktikum https://nav.tum.de/room/0509.EG.943 (from 13:15 to 14:45).