Completed my master's thesis

I have completed my master’s thesis on the topic: Multimodal Gesture Recognition in Artwork Images.

---

Abstract: The thesis investigates the challenge of multi-person gesture recognition in artwork images using single-stage object detection methods, with a focus on improving their classification performance. The current transformer-based state-of-the-art object detection models are effective in localizing persons but are shown to struggle with accurately classifying their gestures. This limitation arises from confining object queries to predefined regions within the image, which restricts access to holistic features essential for accurate gesture classification. To address these limitations, two key modifications are proposed: Gesture-Specific Queries and a Combined Classification Decoder to an existing transformer-based architecture. These modifications are designed to improve its classification accuracy while maintaining localization capabilities. Experimental evaluations demonstrate that these proposed approaches outperform existing methods, establishing a new state-of-the-art in gesture recognition for artwork images on the SensoryArt dataset. Additionally, this study highlights the importance of pose-related features to further improve gesture detection accuracy.