Recherche
Advancing how digital images, video, and 3D experiences are created, processed, and experienced.
We study the problem of image captioning, i.e., automatically describing an image by a sentence. This is a challenging problem, since different from other computer vision tasks such as image classification and object detection, image…
We study the problem of 3D object reconstruction and recognition. For reconstruction, we aim at developing algorithms and systems to lower down the barrier of 3D reconstruction for common users. In this way, we can…
Three-dimensional (3D) user interfaces are popular in movies. Moreover, there are now many systems that enable people to interact with 3D content, including computer games. Based on reflections on the capabilities and limitations of both…
Graphics Processing Units (GPUs) are an attractive target for graph algorithms because they support massively parallel execution and possess much higher memory bandwidths than CPUs and FPGAs. However, graph programs are also highly irregular and…
Click to download video We develop the MagicBrush system, a novel painting-based image search engine. This system enables users to draw a color sketch as a query to find images. Different from existing works on…
