Papers
3
Total Citations
54
H-Index
3
About
Yu-Ting Hsu is a researcher at the intersection of computer vision, multimodal learning, and intelligent service robotics. Her work focuses on enabling robots to perceive and interact with human environments more naturally, particularly through advanced image captioning and object classification systems. Hsu’s major contributions include developing visual image caption generation frameworks that allow service robots to produce context-aware, human-readable descriptions of their surroundings—a critical step toward more intuitive human-robot interaction. Her 2019 paper on this topic has garnered 38 citations, reflecting its influence in the field. She further advanced this area with a multi-modal, human-aware caption system that integrates diverse sensory inputs to improve contextual understanding in real-world robotic applications. In parallel, Hsu has addressed the practical challenge of reliable object classification for household chores, using convolutional neural networks to minimize misclassification—a key safety and functionality concern for domestic robots. Her work is notable for bridging high-level AI tasks like image captioning with the concrete demands of service robotics, making her research both theoretically rich and practically impactful for the next generation of intelligent home assistants.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3