Junsong Yuan

TL;DR: A review of the major progress in visual pattern discovery is provided, categorizing the existing methods into two groups: bottom‐up pattern discovery and top‐down pattern modeling.

TL;DR: A fast approach to detect salient objects from images with extensive results on different types of saliency maps with a public dataset of five thousand images shows the advantages of the approach as compared to some state-of-the-art methods.

TL;DR: This work introduces a novel PU learning method, which can tackle the situation where an unlabeled data set is mostly composed of positive instances, and starts by using a linear model to extract the most reliable negative instances followed by a self-learning process to add reliable negative and positive instances with different speeds based on the estimated positive class prior.

TL;DR: This work proposes a randomized approach to deriving spatial context, in the form of spatial random partition, which offers three benefits: the aggregation of the matching scores over multiple random patches provides robust local matching; the matched objects can be directly identified on the pixelwise confidence map, which results in efficient object localization.

TL;DR: This work adapt DGCNN to perform action recognition by recognizing 3D geometry features in spatio-temporal space of the event data using Dynamic Graph CNN (DGCNN) which directly takes 3D points as input and is successfully used for 3D object recognition.