We present and discuss graphical model sketches [KBG16], a set of three algorithms for approximating the maximum likelihood estimates of the marginal and conditional probabilities within a Bayesian network. In particular, we motivate the problem at hand, highlight the commonalities among the three algorithms and contextualize them within the framework of frequency estimation, providing color al...

We study three transformation-invariant shape descriptors and evaluate their relative strengths in the context of content-based retrieval of graphical sketches. We show that the use of a combination of different shape representations may lead to a significant improvement of retrieval performance and identify an optimal combination that proves robust across different data sets and queries.

Sketch is a probabilistic data structure, and is widely used for per-flow measurement in network. The most common sketches are the CM sketch and its several variants. However, given a limited memory size, these sketches always significantly overestimate some flows, exhibiting poor accuracy. To address this issue, we proposed a novel sketch named the Bloom sketch, combining the sketch with the B...

Sketch portrait generation is of wide applications including digital entertainment and law enforcement. Despite the great progress achieved by existing face sketch generation methods, they mostly yield blurred effects and great deformation over various facial parts. In order to tackle this challenge, we propose a novel composition-aided generative adversarial network (CA-GAN) for sketch portrai...

Sketch-N-Make is a prototype system that enables individuals to create dimensioned designs quickly for a restricted, but broadly useful, domain of machined metal and plastic prismatic parts. Process plans, xturing, tool selection, feeds and speeds, and toolpaths are automatically generated from the designs allowing parts to be manufactured on a machining center with the aid only of a technician...

We present a new sketch-based product form exploration technique that works from images and sketches of existing products. At the heart of our approach, is a multi-stroke curve beautification method and a curve-based image deformation algorithm. The proposed approach converts groups of strokes into piecewise clothoid curves in order to produce visually pleasing shapes. The deformation diffusion...