J. Aníbal Arias

Learn More
In this paper, we propose a method for combining audio and video for segmentation and classification. The objective of segmentation is to detect the category change point such news to advertisement. The classification system classify the audio-video data into one of the predefined categories such as news, advertisement, sports, serial and movies. Mel(More)
CHS15 is one of a family of bean genes encoding chalcone synthase, which catalyzes the first reaction in a branch pathway of phenylpropanoid biosynthesis for the production of flavonoid pigments and UV protectants and isoflavonoid-derived phytoalexins. The functional architecture of the CHS15 promoter was dissected by a novel homologous plant in vitro(More)
It is well established that milk production of the dairy cow is a function of mammary epithelial cell (MEC) number and activity and that these factors can be influenced by diverse environmental influences and management practises (nutrition, milk frequency, photoperiod, udder health, hormonal and local effectors). Thus, understanding how the mammary gland(More)
A potential role for epigenetic mechanisms in the regulation of mammary function in the dairy cow is emerging. Epigenetics is the study of heritable changes in genome function that occur because of chemical changes rather than DNA sequence changes. DNA methylation is an epigenetic event that results in the silencing of gene expression and may be passed on(More)
This paper describes a solution for the organization and management of multimedia collections in digital libraries. The Video U-DL-A (VUDLA) system allows for storage, indexing and annotation of multimedia documents in such a way that textand image-based queries can be issued in order to retrieve specific scenes from digital video collections. Technologies(More)
In this paper we propose an unsupervised approach to speaker segmentation using autoassociative neural network (AANN). Speaker segmentation aims at finding speaker change points in a speech signal which is an important preprocessing step to audio indexing, spoken document retrieval and multi speaker diarization. The method extracts the speaker specific(More)
We discuss the implications of the use of current multimedia collections and posit that it is possible to build what we term fourth-phase digital libraries (4PDLs). In 4PDLs users can take advantage of both the powerful audiovisual channels and the proven practices developed for media such as text. We demonstrate how various technologies can be integrated(More)
  • 1