Month: October 2014

Data-driven detection and self-learning camera

Place: Large Lecture Room Affiliation: Xerox Research Centre, Grenoble, France. The first part of the talk will cover “Data-driven detection”: an approach to detect prominent objects in images WITHOUT using sliding windows, just computing a single feature vector per image. We formulate

Posted in Seminars

Learning to Represent Handwritten Shapes and Words for Matching and Recognition

Place: Large Lecture Room Affiliation: Universitat Autònoma de Barcelona, Computer Vision Centre, Barcelona. Spain. Committee Members: Dr. Karteek Alahari – committee INRIA Grenoble, France. Dr. Marçal Rusinyol- Centre de Visió per Computador – UAB, Barcelona, Spain. Dr. Jose A. Rodrguez

Posted in Phd

Scene Understanding in Videos: Segmentation, Tracking and Pose Estimation

  Place: Large Lecture Room Affiliation: Inria Grenoble – Rhône-Alpes – LEAR Project, France.   This talk will focus on some of our work in the context of the scene understanding problem, in particular, in the use of temporal information. Video provides

Posted in Seminars

Characteristics of Characters and Contexts of Texts: Several topics around Scene Texts

  Place: Large Lecture Room Affiliation: Kyushu University, Japan.   Now OCR is extending its target from scanned documents to scene images. Please look around and find texts around you — there may be various texts printed in various fonts. Thinking about

Posted in Seminars

A polynomial algorithm for HMM decoding with long-distance dependencies

Place: Large Lecture Room Affiliation: Computer Vision Centre, Barcelona, Spain.   In this talk, dynamic programming is represented as a Max-Flow/Min-Cut problem, for which polynomial algorithm exists. For a linear HMM topology, the relation between dynamic programming and Viterbi decoding allows

Posted in Seminars

A polynomial algorithm for HMM decoding with long-distance dependencies

Place: Large Lecture Room Affiliation: Large Lecture Room In this talk, dynamic programming is represented as a Max-Flow/Min-Cut problem, for which polynomial algorithm exists. For a linear HMM topology, the relation between dynamic programming and Viterbi decoding allows also the HMM

Posted in Seminars

A computational model of eye guidance, searching for text in real scene images

Place: Large Lecture Room Affiliation: Universitat Autònoma de Barcelona, Computer Vision Centre, Barcelona. Spain. Committee Members: Prof. Angelo Marcelli – Dept. DIEM Universita degli studi di Salermo, Italy. Prof. Sophie Wuerger – Committe Dept. Psychological Sciences University of Liverpool, UK.

Posted in Phd

Doctorat industrial: Document Forensics for Identity Fraud Detection using Mobile Images

Icar Vision Systems and Universitat Autònoma de Barcelona offers a Industrial Doctoral fellowship.   You can see all the information here 

Posted in JobCaducat

A CVC Business project selected at the Model2Market program

Knowxel, a spin-off developed by researchers at the CVC will be at Mexico City to follow the 3Days2Spin program thanks to Model2Market. During the stay at Mexico they will be working on issues such as strategies, models and methodologies of

Posted in News