Learning to estimate 3D geometry in a single image by watching unlabeled videos via deep
convolutional network is attracting significant attention. In this paper, we introduce a “3D as …

This paper proposes a method for handwritten Chinese/Japanese text (character string)
recognition based on semi-Markov conditional random fields (semi-CRFs). The high-order …

Natural language processing covers a wide variety of tasks with token-level or sentence-
level understandings. In this paper, we provide a simple insight that most tasks can be …

Dependencies among neighboring labels in a sequence are important sources of
information for sequence labeling and segmentation. However, only first-order …

Named entity recognition (NER) in Chinese social media is an important, but challenging
task because Chinese social media language is informal and noisy. Most previous methods …

Structured prediction is the problem of learning a function that maps structured inputs to
structured outputs. Prototypical examples of structured prediction include part-of-speech …

We consider a framework for structured prediction based on search in the space of complete
structured outputs. Given a structured input, an output is produced by running a …

We introduce the M-modes problem for graphical models: predicting the M label
configurations of highest probability that are at the same time local maxima of the probability …

Semi-Markov CRF has been proposed as an alternative to the traditional Linear Chain CRF
for text segmentation tasks such as Named Entity Recognition (NER). Unlike CRF, which …

The computational complexity of linear-chain Conditional Random Fields (CRFs) makes it
difficult to deal with very large label sets and long range dependencies. Such situations are …