In many image and video collections, we have access
only to partially labeled data. For example, personal photo
collections often contain several faces per image and a caption
t...
Benjamin Sapp, Benjamin Taskar, Chris Jordan, Timo...
We propose a new multiple instance learning (MIL) algorithm to learn image categories. Unlike existing MIL algorithms, in which the individual instances in a bag are assumed to be...
Guo-Jun Qi, Xian-Sheng Hua, Yong Rui, Tao Mei, Jin...
The success of tensor-based subspace learning depends heavily on reducing correlations along the column vectors of the mode-k flattened matrix. In this work, we study the problem ...
Shuicheng Yan, Dong Xu, Stephen Lin, Thomas S. Hua...
Many NLP tasks rely on accurately estimating word dependency probabilities P(w1|w2), where the words w1 and w2 have a particular relationship (such as verb-object). Because of the...
Kristina Toutanova, Christopher D. Manning, Andrew...
Cross-language latent semantic indexing is a method that learns useful languageindependent vector representations of terms through a statistical analysis of a documentaligned text...