Semi-supervised video segmentation using tree structured graphical models

We present a novel, implementation friendly and occlusion aware semi-supervised video segmentation algorithm using tree structured graphical models, which delivers pixel labels alongwith their uncertainty estimates. Our motivation to employ supervision is to tackle a task-specific segmentation problem where the semantic objects are pre-defined by the user. The video model we propose for this problem is based on a tree structured approximation of a patch based undirected mixture model, which includes a novel time-series and a soft label Random Forest classifier participating in a feedback mechanism. We demonstrate the efficacy of our model in cutting out foreground objects and multi-class segmentation problems in lengthy and complex road scene sequences. Our results have wide applicability, including harvesting labelled video data for training discriminative models, shape/pose/articulation learning and large scale statistical analysis to develop priors for video segmentation. © 2011 IEEE.

A Plant Needs Ants like a Dog Needs Fleas: Myrmelachista schumanni Ants Gall Many Tree Species to Create Housing

Hundreds of tropical plant species house ant colonies in specialized chambers called domatia. When, in 1873, Richard Spruce likened plant-ants to fleas and asserted that domatia are ant-created galls, he incited a debate that lasted almost a century. Alth

A single amino acid defines cross-species reactivity of tree shrew (Tupaia belangeri) CD1d to human invariant natural killer T (iNKT) cells

P>The non-classical major histocompatibility complex (MHC) class I molecule CD1d presents lipid antigens to invariant natural killer T (iNKT) cells, which are an important part of the innate immune system. CD1d/iNKT systems are highly conserved in evoluti

KARYOTYPE AND BANDING-PATTERNS OF FEA TREE RAT (CHIROMYSCUS-CHIROPUS)

Fea's tree rat (Chiromyscus chiropus) is a very rare species which there are only a few specimens in the world. The chromosomes of two male specimens, collected from Xishuanbanna, Yunnan, are analysed by several banding technique (G-, C-bands, as well as Ag-staining). The diploid chromosome number is 22, and autosomes comprise 5 pairs of metacentrics, 2 pairs of subacrocentrics, and 3 pairs of acrocentrics. The X chromosome is a acrocentric, and Y is a micro-chromosome, almost a point, which could be a marker chromosome of the species and the genus. The centromeric C-bands are very faint, and C-bands of Nos. 1, 2, 9 and Y chromosome are negative. Only one pair Ag-NORs was found on No. 10 in the silver-stained karyotype. The relationship between morphologic and chromosomal features was discussed, and C-banded karyotype evolutionary trend has also been discussed. Moreover, the conventional karyotype of Niviventer confucianus was described.

Unsupervised intra-lingual and cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction

Hidden Markov model (HMM)-based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset. Speaker adaptation methods used in the field of HMM-based automatic speech recognition (ASR) are adopted for this task. In the case of unsupervised speaker adaptation, previous work has used a supplementary set of acoustic models to estimate the transcription of the adaptation data. This paper first presents an approach to the unsupervised speaker adaptation task for HMM-based speech synthesis models which avoids the need for such supplementary acoustic models. This is achieved by defining a mapping between HMM-based synthesis models and ASR-style models, via a two-pass decision tree construction process. Second, it is shown that this mapping also enables unsupervised adaptation of HMM-based speech synthesis models without the need to perform linguistic analysis of the estimated transcription of the adaptation data. Third, this paper demonstrates how this technique lends itself to the task of unsupervised cross-lingual adaptation of HMM-based speech synthesis models, and explains the advantages of such an approach. Finally, listener evaluations reveal that the proposed unsupervised adaptation methods deliver performance approaching that of supervised adaptation.

DT-MRI data visualisation using the dual tree Complex Wavelet transform

In this paper a novel visualisation method for diffusion tensor MRI datasets is introduced. This is based on the use of Complex Wavelets in order to produce "stripy" textures which depict the anisotropic component of the diffusion tensors. Grey-scale pixel intensity is used to show the isotropic component. This paper also discusses enhancements of the technique for 3D visualisation. © 2004 IEEE.