The given topics are not fixed. If you want to bring your own ideas, adapt the given ones, we can talk. Topics are given in English to accomodate for foreign students, everything can be submitted in either German or English.

?

Open Topics:

• [Bachelor Thesis/Master Thesis/Project Module] Generating Feedback for Motor Learning: Human Motor Learning is heavily reliant on a mixture of constant self-improving behaviours (think: learning how to walk) and active feedback (think: learning proper high-jump technique). For learning environments where no high quality active feedback exists, i.e. no coaches are available, it is important to be able to still have feedback that is good enough to prevent injury.
  Recently we developed a method for providing active feedback to javelin throwers, showing them technique improving pose sequences. We were however also able to show, that this is not sufficient for athletes to apply this feedback.
  Your goal in this work will be to develop a system that is able to either provide textual feedback or improve the methodology of generating the technique improving pose sequences.
  
  Resources:
  ?
  • ExpertAF:?CVPR 2025 Open Access Repository?(Most recent, high quality feedback providing system)
  • GANterfactual: Frontiers | GANterfactual—Counterfactual Explanations for Medical Non-experts Using Generative Adversarial Learning?(Base method for generating counterfactual feedback that we used)
    ?
• [Bachelor Thesis/Master Thesis/Project Module] Isolated Sign Language Recognition using SMPL pose and shape parameters:?Isolated Sign Language Recognition is a classification tasks where single words in a given sign language are predicted from video. One of the main problems working with sign language is that there is only little training data available. To counteract this problem, pre-processing steps are necessary to reduce the information in a given video into a smaller set of relevant information. While the body hands is by far not the only relevant features of sign language (face, hands mouth movements and other manipulators are also important) they do represent crucial information of most words.
  SMPL is a parametrics body model, i.e. a 3D body mesh model with a transformation function, that transforms a "base" body and a set of parameters into a body mesh. SMPLer-X is a system that can predict these transformation parameters from an input image for 3D body mesh reconstruction.
  In this work you will implement and evaluate a system, that performs Isolated Sign Language Recognition on SMPL parameters extracted using SMPLer-X.
  
  Resources:
  ?
  • SMPLer-X:?https://github.com/SMPLCap/SMPLer-X
  • SMPL:?https://smpl.is.tue.mpg.de/
  • Isolated Sign Language Recognition:?https://tinyurl.com/mrxptkvs
    ?
• [Bachelor Thesis/Master Thesis/Project Module] Using Sapiens Features and Attentive Probing for Isloated Sign Language Recognition: Sapiens is a foundation model specialized on understanding human physiology. It was trained on millions of images of humans in a self-supervised manner using a Masked Autoencoder (MAE) approach. It performs very well on keypoint estimation, semantic segmentation, depth estimation, and normal estimation tasks. The features output by the backbone model can however be used for a great number of different tasks.
  Attentive Probing is a relatively new approach to perform classification on a given set of input features. It is hypothesised that this is the case in settings, where the features contain high degrees of semantic information.
  Isolated Sign Language Recognition is a classification task where single words in a given sign language are predicted.
  In this work you will implement a system that uses Sapiens and Attentive Probing for the prediction task and compare your results against other existing systems.
  
  Resources:
  ?
  • Sapiens:?https://www.meta.com/emerging-tech/codec-avatars/sapiens
  • Attentive Probing:?https://arxiv.org/abs/2202.03026
  • Isolated Sign Language Recognition:?https://tinyurl.com/mrxptkvs

In-Progress Topics:

• [Bachelor Thesis SS26] Isolated Sign Language Recognition using MANO pose and shape parameters: Isolated Sign Language Recognition is a classification tasks where single words in a given sign language are predicted from video. One of the main problems working with sign language is that there is only little training data available. To counteract this problem, pre-processing steps are necessary to reduce the information in a given video into a smaller set of relevant information. While hands are by far not the only relevant features of sign language (face, body, mouth movements and other manipulators are also important) they do represent crucial information of most words.
  MANO is a parametric hand model, i.e. a 3D hand mesh model with a transformation function, that transforms the "base" hand and a set of parameters into a hand mesh. HaMeR is a deep neural network that can predict these transformation parameters from an input image for 3D hand mesh reconstruction.
  In this work we are implementing a system, that performs Isolated Sign Language Recognition on MANO parameters extracted using HaMeR.
  
  Resources:
  ?
  • HaMeR:?https://geopavlakos.github.io/hamer/
  • MANO:?https://mano.is.tue.mpg.de
  • Isolated Sign Language Recognition:?https://tinyurl.com/mrxptkvs

Completed Seminar-/ and Thesis Papers:

• [Bachelor Thesis SS25] Implementation of Keyword Spotting for Alignment of Subtitles to German Sign Language: One of the main problems in automatic sign language translation research is data scarcity. One way to counteract this problem could be to use data acquired from public TV broadcasts, some of which provide their own sign language translations. However, these are often direct translation from spoken German, i.e. not scripted, and, if so, often do not have a correct temporal alignment with the spoken German subtitles.
  Thus, the data can not be used for training translation models.
  In this work we are investigated, if we can perform (some) alignment for a set of known words. To this end, we finetuned a known model for Visual Keyword Spotting (VKS), originally trained on videos of spoken English, and adapted it to German. We were able to show, that:
  ?
  • Even with small-scale finetuning (small subset of the GLips dataset), KWS-Net is able to perform VKS on videos of German speakers.
  • Lemmatization of the detected words might help improve recognition accuracy
    
    ?
• [Bachelor Thesis WS24/25] Autonomous Re-Identification of Humans by Mobile Robots in an Indoor Environment: Robotic assistants are a current hot-topic in human-centered artificial intelligence research. For these assistants to perform well in the wild, they need to be able to (re-)identify human operators and/or other humans they are interacting with.
  In this work a student implemented a set of ROS nodes deployable on an NVIDIA Jetson machine, that can be used to detect and re-identify known persons in real-time.