Martina Toshevska
Papers
2
Total Citations
9
H-Index
2
About
Martina Toshevska is a researcher at the intersection of computer vision, natural language processing, and human-robot interaction. Her work focuses on enabling machines to not only understand visual scenes but also to respond to human emotional cues. In her highly cited 2020 paper, "Explorations into Deep Learning Text Architectures for Dense Image Captioning," she advanced the field of dense image captioning—a task that generates detailed, context-rich descriptions of image regions. This work, which has garnered 6 citations, holds promise for applications in assistive technologies for the visually impaired, robotics, and automated storytelling. Toshevska also explores affective computing in her 2018 study, "Emotion-Aware Teaching Robot: Learning to Adjust to User’s Emotional State," where she developed a robot capable of adapting its behavior based on a user’s emotional feedback. With 3 citations, this research contributes to the growing field of socially intelligent robotics, particularly in educational settings. Her interdisciplinary approach bridges deep learning architectures with human-centered design, making her a notable voice in creating more perceptive and empathetic AI systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2