Place: Large lecture room. Affiliation:  Departament de Matemà tica Aplicada i Anà lisi. Universitat de Barcelona, Spain. This seminar is a summary of Adriana Romero Soriano’s PhD thesis work. Deep learning has recently been enjoying an increasing popularity due to its success …
Assisting the training of deep neural networks with applications to computer vision Read More »
Place: Large lecture room. Affiliation: School of Media, Design and Technology, University of Bradford, U.K. With the recent growth in the number and complexity of imaging devices comes a vast amount of image data, particularly from data intensive devices …
Place: Large lecture room. Affiliation:  Instituto Politécnico Nacional, Mexico. My research experience is mainly in Machine Translation (MT), although I have also worked in Automatic Speech Recognition (ASR) and Information Retrieval (IR). In this talk, I will overview several ASR, …
Advances in Statistical Machine Translation in the last 10 years Read More »
Place: Large lecture room. Affiliation:Â Computer Vision group at Xerox XRCE. Grenoble, France. In this talk I will present some recent work carried out at the Computer Vision group at Xerox XRCE. In the first part of the talk I …
Place: Large lecture room. Affiliation: KIIS Research Center at Università Ca’ Foscari Venezia, Italy. Graph-based representations have been used with considerable success in computer vision in the abstraction and recognition of object shape and scene structure due to its ability …
Structural Models for Deformable Shape Recognition Read More »
Place: Seminari Room (1st floor) Affiliation: KIIS Research Center at Università Ca’ Foscari Venezia, Italy. The main point made by game theorists is to shift the emphasis from optimality criteria to equilibrium conditions. As it provides an abstract theoretically-founded framework to elegantly …
Place: Large Lecture Room. Affiliation: Institut de Robòtica i Informà tica Industrial, Barcelona, Spain. In this talk I will review my principal research topics in the past few years. I will start presenting linear formulations to efficiently estimate pose for calibrated and non-calibrated …
Place:Â Large Lecture Room. Affiliation: LEAR Team, INRIA, Grenoble, France. Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. …
Place: Large lecture room. Affiliation: Universitat Pompeu Fabra, Barcelona, Spain. Considering the camera imaging pipeline for color image processing: Color stabilization, blind gamma estimation, and color characterization Two main topics will be presented in this seminar. …
Traditional approaches to document retrieval focus on conversion to electronic text followed by indexing of the text content. Recently some work in the community has focused on indexing document image content directly. In this talk, we will overview work at …
