AI & ML interests

Computer Vision + Human Sketch

The ultimate vision for SketchX is to understand how seeing can be explained by drawing. In other words, how better understanding of human sketch data can be translated to insights on how human visual systems operate, and in turn how such insights can benefit computer vision and cognitive science at large.

SketchX has been actively investigating all aspects of sketch research since 2012. Problems we study range from conventional tasks such as sketch recognition and sketch synthesis, to those pioneered within, e.g., fine-grained sketch-based image retrieval and memory-aware forensic sketch analysis.

SketchX has established itself as a world-leading research lab on human sketch analytics, and continues to publish sketch-specific papers in top venues. It had enjoyed many achievements both academically including a Best Science Paper Award at BMVC’15, and commercially including collaborations with law enforcements, and on-line retailers.

Latest research -- DreamWire
Latest research -- DemoFusion

models

None public yet

datasets

None public yet