One of the main challenges in interactive concept-based video search is the insufficient relevant sample problem, especially for queries with complex semantics. To address this pr...
Jin Yuan, Zheng-Jun Zha, Zhengdong Zhao, Xiangdong...
Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised man...
Linear Discriminant Analysis (LDA) has been a popular method for extracting features which preserve class separability. The projection vectors are commonly obtained by maximizing ...
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail we are given a set ...