Publications home
A Continuum between Serendipitous Browsing and Query-based Search for Multimedia Information Access
at
| Julien Ah-Pine, Jean-Michel Renders, Marie-Luce Viaud |
| AMR 2009 (International Conference on Adaptive Multimedia Retrieval), Madrid, Spain, 24-25 September, 2009 |
This paper deals with information seeking in a multimedia database. In such a context, we assume that the search process is complex, dynamic and multi-faceted. We suppose moreover, that the information need with respect to a topic, can change during a same search session, going from a simple lookup search to a thorough discovery of connected subtopics. We propose a system that aims at addressing these challenges. It couples serendipitous browsing and query-based search in a smooth manner. The main features of our proposal that we want to underline are the following ones. The system offers two levels, global and local, of visualizing the context of the information seeking task and it also allows to view and search the data using either monomodal or cross-modal similarities. Furthermore, the system integrates a new relevance feedback model that takes into account the multimodal nature of the data in a flexible way and a combination of two parameters, the locality and forgetting factors, that allows to design adaptive metrics in the interactive search process. These functionalities are aimed at offering tools to the user in order to solve information seeking tasks efficiently. A preliminary user-centered evaluation of our system, that we also present in this paper, gives encouraging results.
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
VISION
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.