… at the image-level to those contextually derived semantic regions. First, we propose a bi-layer
sparse coding formulation for uncovering how an image or semantic region can be …

… As aforementioned, the reconstructions of candidate regions are guided with a bi-layer
sparsity prior, which indicates that we prefer to select few patches from few images. Moreover, we …

… group lasso encode additional prior information. … Based on its sparse codes, the region
to be labeled is connected to … Previous work has shown the effectiveness of bi-layer sparse …

… To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior …
users and compared the results to human-labeled ground-truth and results from other methods. …

… bi-layer sparsity into this kind of hierarchical model, ie, topic … coding formulation to address
the task of labelto-region … The first term F(Θ, β) is a topic model with bi-layer sparsity priors…

… tags and image regions, ie localize tags to image regions, so as … level sparsity when taking
spatial dependency prior knowledge … Moreover we intend to compare with the BiLayer sparse …

… -to-region problem. Bi-layer sparse coding contains the sparsity constraints on two layers:
patch-to-patch reconstruction … Label to region by bi-layer sparsity priors. In ACM MM, 2009. …

… label-to-region problem by sparse modeling in the second part. The ability to annotate images
with related text labels at the semantic region-… ) Label to Region by Bi-Layer Sparsity Priors…

… The reconstructions of candidate regions are with sparsity prior, … the proposed Label-to-Region
Assignment vis Sparse … proposed bi-layer sparse coding formulation in the label to region …

… Note that no data with ground truth label-to-region relations are provided as priors for this …
Besides, the authors also apply the bi-layer sparse coding framework to perform multi-label …