AAAI
2012
12 years 2 months ago
2012
This paper concerns learning and prediction with probabilistic models where the domain sizes of latent variables have no a priori upper-bound. Current approaches represent prior d...
CVPR
2012
IEEE
12 years 2 months ago
2012
IEEE
In this paper, we tackle the problem of understanding the temporal structure of complex events in highly varying videos obtained from the Internet. Towards this goal, we utilize a...
CVPR
2012
IEEE
12 years 2 months ago
2012
IEEE
The bag-of-words (BoW) model treats images as an unordered set of local regions and represents them by visual word histograms. Implicitly, regions are assumed to be identically an...
SIGIR
2012
ACM
12 years 2 months ago
2012
ACM
Web search components such as ranking and query suggestions analyze the user data provided in query and click logs. While this data is easy to collect and provides information abo...
CORR
2012
Springer
12 years 8 months ago
2012
Springer
Given a set of experiments in which varying subsets of observed variables are subject to intervention, we consider the problem of identifiability of causal models exhibiting late...
EMNLP
2011
13 years 5 days ago
2011
Conversations provide rich opportunities for interactive, continuous learning. When something goes wrong, a system can ask for clarification, rewording, or otherwise redirect the...
EMMCVPR
2011
Springer
13 years 5 days ago
2011
Springer
The recently proposed ImageNet dataset consists of several million images, each annotated with a single object category. However, these annotations may be imperfect, in the sense t...
ICCV
2011
IEEE
13 years 13 days ago
2011
IEEE
We describe a directed bilinear model that learns higherorder groupings among features of natural images. The model represents images in terms of two sets of latent variables: one...
ICCV
2011
IEEE
13 years 13 days ago
2011
IEEE
This paper proposes a very general max-margin learning framework for distance-based clustering. To this end, it formulates clustering as a high order energy minimization problem w...
ACL
2011
13 years 4 months ago
2011
Graph-based dependency parsing can be sped up significantly if implausible arcs are eliminated from the search-space before parsing begins. State-of-the-art methods for arc filt...