Login
Differences
This shows you the differences between two versions of the page.
| — |
teaching:ws2025:cv3 [2025/09/25 10:25] (current) Nikita Araslanov created |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| + | ~~NOTOC~~ | ||
| + | ---- | ||
| + | |||
| + | ===== Computer Vision III: Detection, Segmentation and Tracking (IN2375) ===== | ||
| + | |||
| + | == Overview == | ||
| + | Computer Vision III offers a comprehensive review of methods for high-level computer vision tasks: object detection, image segmentation and object tracking. | ||
| + | These tasks are one of the most compelling applications of computer vision in the real world. | ||
| + | Research on these applications is still very active and highly impactful in computer vision. | ||
| + | The material of this course spans the recent literature leveraging deep learning, as well as more classical optimisation-based and probabilistic methods. | ||
| + | |||
| + | |||
| + | |||
| + | == Registration == | ||
| + | To attend the course, please register in [[https:// | ||
| + | Keep in mind that you will have to register for the exam separately later on. | ||
| + | |||
| + | == Course website == | ||
| + | All course material, announcements and the discussion forum will be provided on [[https:// | ||
| + | |||
| + | |||
| + | == Prerequisites == | ||
| + | * Strongly recommended: | ||
| + | * Mathematical background: Linear algebra and calculus. | ||
| + | * Knowledge of Python is mandatory. | ||
| + | * Knowledge of PyTorch is highly recommended. | ||
| + | |||
| + | |||
| + | == Schedule == | ||
| + | |||
| + | ^ What ^ When ^ Where ^ Who ^ | ||
| + | | Lecture | ||
| + | | Exercise | ||
| + | |||
| + | == Videos (preview) == | ||
| + | |||
| + | * [[https:// | ||
| + | |||
| + | == Contact == | ||
| + | If you have any questions that may be relevant to other students, please post in the forum on Moodle. | ||
| + | For individual inquiries, you can send us an email to [[mailto: | ||
| + | |||
| + | == Acknowledgement == | ||
| + | The course material is based on the previous iterations, which were originally developed by Prof. Laura Leal-Taixé. | ||
