Research on haptic rendering involving complex contact states and compliant motion among curved objects.
Real-time adaptive robot motion planning
Semantics-based Image Classification, focusing on answering the following questions:
Salient object detection. What's a salient object? How to detect the defined salient objects? How to characterize the salient objects?
Automatic semantic image annotation via salient object detection. What are the relationships among the semantic visual concepts and the salient objects? How to evaluate these determined relationships?
Image database management and search engine design. How to manage large-scale image databases? What kind of image search engine can let the naive users to specify their queries?
Semantic Video Classification, Indexing and Retrieval
Novel content-based video analysis technique to obtain the salient objects and principal video shots from long MPEG videos
Hierarchical database management structure to define and refine the semantic meanings of video data in different levels of abstraction
Probabilistic semantic video classifier to bridge the semantic gap between the low-level visual features and the high-level visual concepts
Probabilistic technique for compact video database representation and indexing
Hierarchical visual summarization and presentation technique to enable fast video database browsing in different levels over IP networks.