About Me

comments Comments Off on About Me
By , February 3, 2016

Lamberto BallanI am an Assistant Professor (tenure track) of Computer Science at University of Padova, Italy. Previously, I was a senior post-doctoral researcher at Stanford University – AI Lab – and Univ. of FlorenceMICC, supported by a prestigious Marie Curie Fellowship from the European Commission under the FP7-2013-IOF programme.

I got my Ph.D. in computer engineering, multimedia and telecommunication in 2011 and my Laurea degree in computer engineering in 2006, both from the Univ. of Florence (Italy). I also spent a quarter at the Signal and Image Processing department at Telecom ParisTech (France) in 2010.

My research interests lie at the boundary of Computer Vision and Multimedia. The main focus of my current research is on designing learning algorithms that make the most effective use of contextual knowledge in presence of sparse and noisy labels, such as in the case of web data. Some examples are automatic image/video annotation, large-scale visual recognition, web mining, social media analysis.

Curriculum Vitae / Google ScholararXivDBLP / ORCID

ICCV’15 Paper on Image Annotation by Exploiting Image Metadata

comments Comments Off on ICCV’15 Paper on Image Annotation by Exploiting Image Metadata
By , November 1, 2015

GraphNeighborModelOur paper “Love Thy Neighbors: Image Annotation by Exploiting Image Metadata”, by J. Johnson*, L. Ballan* and L. Fei-Fei (* equal contribution), has been accepted to ICCV 2015. A pre-print is now available on arXiv.

Some images that are difficult to recognize on their own may become more clear in the context of a neighborhood of related images with similar social-network metadata. We build on this intuition to improve multilabel image annotation. Our model uses image metadata nonparametrically to generate neighborhoods of related images using Jaccard similarities, then uses a deep neural network to blend visual information from the image and its neighbors.

ACM MM’15 Tutorial on Image Tag Assignment, Refinement and Retrieval

comments Comments Off on ACM MM’15 Tutorial on Image Tag Assignment, Refinement and Retrieval
By , October 29, 2015

12183790_10153302893771359_4417098406233994063_oWe gave a tutorial on “Image Tag Assignment, Refinement and Retrieval” at ACM MM 2015, based on our recent survey. Our tutorial focuses on challenges and solutions for content-based image retrieval in the context of online image sharing and tagging. We present a unified review on three closely linked problems: tag assignment, tag refinement, and tag-based image retrieval. We introduce a taxonomy to structure the growing literature, understand the ingredients of the main works, and recognize their merits and limitations.

We provided also an hands-on session with the main methods, software and datasets. All data, code and slides are online at: http://www.micc.unifi.it/tagsurvey

SAILORS 2015: Tutorial on Nearest Neighbors for Image Classification

comments Comments Off on SAILORS 2015: Tutorial on Nearest Neighbors for Image Classification
By , August 7, 2015

Lamberto Ballan - Stanford SAILORS 2015 - kNN tutorialI have just given a tutorial on kNN at the Stanford Artificial Intelligence Laboratory’s Outreach Summer program (SAILORS). SAILORS is designed to expose high school students in underrepresented populations to the field of Artificial Intelligence.

The slides are available on this page and the Matlab code is also available for download. This is an updated version of the code used in class and should work also on Octave.

Data-Driven Tag Refinement and Localization in Web Videos

comments Comments Off on Data-Driven Tag Refinement and Localization in Web Videos
By , June 1, 2015

video-tag-localizationOur paper “A Data-Driven Approach for Tag Refinement and Localization in Web Videos”, by myself, Marco Bertini, Giuseppe Serra, Alberto Del Bimbo, has been accepted for publication in Computer Vision and Image Understanding (CVIU) and is now available online.

Alberto Del Bimbo has been also invited to present our work at the Workshop on Large-Scale Video Search and Mining at CVPR 2015.

Estimating the relevance of a specific tag with respect to the visual content of a given image and video has become the key problem in order to have reliable and objective tags. With video tag localization is also required to index and access video content properly. In this paper, we present a data-driven approach for automatic video annotation by expanding the original tags through images retrieved from photo-sharing website, like Flickr, and search engines such as Google or Bing. Compared to previous approaches that require training classifiers for each tag, our approach has few parameters and permits open vocabulary.

Teaching machines to see

comments Comments Off on Teaching machines to see
By , March 18, 2015

visionlabWatch the TED 2015 talk by my postdoc advisor Prof. Fei-Fei Li about the recent advances in computer vision, from the detection and classification of objects in images to algorithms that are able to construct natural descriptions of those images. It is an exciting overview of the current state of the art in computer vision, in which she shares her thoughts on its potential use and impact. http://goo.gl/8O5Fch

Landed and settled in Stanford

comments Comments Off on Landed and settled in Stanford
By , October 11, 2014

Lucia and Lamberto Ballan at StanfordI am finally settled at Stanford University and just started my appointment as postdoctoral scholar in the AI laboratory (SAIL) on a Marie Curie Fellowship from the European Commission.

I started working in Fei-Fei Li‘s Vision Lab. I am also collaborating with Silvio Savarese and Bernd Girod.

ICPR 2014 Tutorial: Hands on Advanced Bag-of-Words Models for Visual Recognition

comments Comments Off on ICPR 2014 Tutorial: Hands on Advanced Bag-of-Words Models for Visual Recognition
By , July 30, 2014

Lamberto Ballan and Lorenzo Seidenari at ICPR 2014

Lorenzo Seidenari and I gave the tutorial “Hands on Advanced Bag-of-Words Models for Visual Recognition” at the ICPR 2014 conference (August 24, Stockholm, Sweden).

All materials – i.e. slides, Matlab code, images and features – and more details can still be found on this webpage.

Marie Curie IOF 2013 Award

comments Comments Off on Marie Curie IOF 2013 Award
By , February 10, 2014

Marie Curie ActionsI have been awarded with a Marie Curie International Outgoing Fellowship (IOF) granted by the European Commission. The Marie Curie IOF is a prestigious and highly competitive fellowship for experienced European scientists to gain new skills and expertise while conducting high-level research in a country outside Europe.

I have been awarded a grant of 272K Euro for the 3-years project “EAGLE: Exploiting semAntic and social knowledGe for visuaL rEcognition”. I will spend the first two years (outgoing phase) at Stanford University.

A Cross-media Model for Automatic Image Annotation

comments Comments Off on A Cross-media Model for Automatic Image Annotation
By , January 27, 2014

nn_flower_kccaOur ICMR 2014 full paper “A Cross-media Model for Automatic Image Annotation” by Lamberto Ballan, Tiberio Uricchio, Lorenzo Seidenari and Alberto Del Bimbo has been accepted for oral presentation and it is now available online.

Automatic image annotation is still an important open problem in multimedia and computer vision. The success of media sharing websites has led to the availability of large collections of images tagged with human-provided labels. Many approaches previously proposed in the literature do not accurately capture the intricate dependencies between image content and annotations. We propose a learning procedure based on KCCA which finds a mapping between visual and textual words by projecting them into a latent meaning space. The learned mapping is then used to annotate new images using advanced nearest-neighbor voting methods.

Panorama Theme by Themocracy