Visual Search in Large Image Collections

Are you going?

54 people going

Location image of event venue

What we'll do

Hello everybody!

The event we all have been waiting! Our first meetup for 2019 is approaching.. Diane Larlus will be presenting on visual search. Below an abstract and some information on Diane.

We hope to see you at Cowork on February 21 at 19h00!

Talk summary

Querying with an example image is a simple and intuitive interface to retrieve information from a collection of images. Such a retrieval task has a wide range of applications, including reverse image search on the web or the automatic organization of personal photo collections. While deep learning rapidly became a key ingredient in the top performing methods for many computer vision tasks, it was falling short when applied to these retrieval tasks. This presentation will show how to successfully apply deep learning representations such as convolutional neural networks to visual search, producing a solution that is both effective and computationally efficient.

In a second part, the presentation will move beyond instance-level retrieval and consider the task of semantic image retrieval in complex scenes, where the goal is to retrieve images that share the same semantics as the query image. Despite being more subjective and more complex, one can show that the task of semantically ranking visual scenes is consistently implemented across a pool of human annotators, and that deep learning models can also be leveraged to automate this task of semantic retrieval.

Short Bio:
​Diane Larlus is a senior research scientist in the Computer Vision group of Naver Labs Europe. She obtained a M.Sc. in Image, Vision and Robotics from UJF/INP, Grenoble, France, in 2005. From 2005 to 2008, she worked as a doctoral candidate at INRIA Grenoble. During the summer 2007, she interned at the JRL/AIST laboratory in Tsukuba, Japan. Diane Larlus obtained a Ph.D. in 2008, from INP Grenoble. From 2008 to 2010, she worked as a post-doc at TU Darmstadt, Germany. She joined the European research lab of Xerox in 2010, which became NAVER LABS Europe in 2017.
Her research focuses on applying machine learning to several computer vision tasks. She is particularly interested in getting a semantic and global understanding of visual scenes. She has recently worked on instance-level and semantic visual search and in representing the structure and geometry of object categories, and in reasoning at the scene-level with images and text. She was an Outstanding Reviewer at ECCV 2016, CVPR 2017 and 2018 and will be an Area Chair for ICCV 2019.