Master's Thesis Reinforcement Learning for Wheeled Bipedal Outdoor Robot with Isaac Lab

Fraunhofer-Gesellschaft

ThesisGerman needed: not said

Still open on 1 Nov

You apply on the company's own website.

Key facts

Subject you study: Electrical Engineering, Computer Science, Cybernetics, Mechatronics, Technical Computer Science

The goal of this master's thesis is to investigate whether and to what extent poses and facial expressions can be used for the recognition of erotic and pornographic image material. First, it should be researched which existing approaches are suitable for addressing the question. Gaps in existing datasets and models should be described and closed with own data and models. Based on the developed methods, it should then be evaluated (1) whether reliable recognition of erotic poses and facial expressions is possible and (2) whether erotic and pornographic images can be distinguished from other categories based on recognized poses and facial expressions. Here, evaluation should be performed on different counter-classes, such as everyday or sports images.
Results: As part of this master's thesis, the following results are to be achieved:
Dataset with annotations for the recognition of erotic poses and facial expressions.
Implementation of new approaches for the classification of poses and facial expressions, both in everyday situations and in erotica and pornography.
Evaluation of the models, both in terms of classification of poses and facial expressions and classification of images (pornographic/erotic/normal).

Electrical Engineering, Computer Science, Cybernetics, Mechatronics, Technical Computer Science or comparable

The goal of this master's thesis is to investigate whether and to what extent poses and facial expressions can be used for the recognition of erotic and pornographic image material. First, it should be researched which existing approaches are suitable for addressing the question. Gaps in existing datasets and models should be described and closed with own data and models. Based on the developed methods, it should then be evaluated (1) whether reliable recognition of erotic poses and facial expressions is possible and (2) whether erotic and pornographic images can be distinguished from other categories based on recognized poses and facial expressions. Here, evaluation should be performed on different counter-classes, such as everyday or sports images.
Results: As part of this master's thesis, the following results are to be achieved:
Dataset with annotations for the recognition of erotic poses and facial expressions.
Implementation of new approaches for the classification of poses and facial expressions, both in everyday situations and in erotica and pornography.
Evaluation of the models, both in terms of classification of poses and facial expressions and classification of images (pornographic/erotic/normal).

Electrical Engineering, Computer Science, Cybernetics, Mechatronics, Technical Computer Science or comparable