Research Works

 

Short bio

 

Adrien Joly is a PhD candidate researching in the field of Context-Awareness / Ambient Services for the Social Communications department of Alcatel-Lucent Bell Labs Applications, in collaboration with the CNRS-LIRIS laboratory and under supervision of Pr. Pierre Maret. He received a Master Degree of Information Technology from the Institut National des Sciences Appliquées de Lyon (INSA-LYON, France) in 2006. Achieved during his exchange program in Queensland University of Technology (Australia), his Master Project was to design and develop an extensible summary navigation system in order to demonstrate the SEO multimedia annotation scheme proposed by his supervisor: Dr. Dian Tjondronegoro. His current interests cover Ambient Intelligence, Pervasive Systems, Ubiquitous Computing, Social Networking, Semantic Web, Mobile Applications, and modular software architecture.

 

Subject of my PhD thesis

 

Title: Leveraging semantic technologies in context-aware social applications

 

At a time when social networking sites have transformed our manners on the Web 2.0, interpersonal communications are becoming easier, more fun and richer. Transposing these manners on the move implies new challenges such as the management of intrusivity of communications, interoperability accross heterogeneous terminals and networks, and context-aware adaptation of applications. The goal of this thesis is to study how semantic technologies can help us address these challenges.

 

Up-to-date version of the subject of my PhD thesis

 

You can also:

• follow updates on my thesis on twitter (hashtag #mythesis)

• read my blog

• follow my activities on FriendFeed (which include my twitter updates and my blog posts).

 

 

Publications

 

For more up-to-date list of publications, please go to my lab's personal page: Adrien Joly's publication

 

You can also:

• check out my profile on CiteULike and BibSonomy, but their publication list is not exhaustive yet

• see the list of conferences and journals I'm interrested in on WikiCFP.

 

 

My work-in-progress prototype: "Contextual Filter for the Ambient Enterprise" (demo paper proposed to SIGIR'09)

 

Context-Awareness, the missing block of Social Networking

 

• Authors: Adrien Joly, Pierre Maret, Johann Daigremont
• To be presented at the Networking Mobile Virtual Knowledge, special session of the PRO-VE'08, the 9th IFIP Working Conference on Virtual Enterprises, Poznan, POLAND. 8 - 10 September 2008
• Abstract: Social Networking Sites (SNS) have become increasingly popular with the rise of the Web 2.0 in which internet users are invited to contribute and interact on web sites. Although many SNS are criticized for privacy issues, most of their users tend to share more and more personal (and sometimes intimate) content on these communities. This creates new opportunities for them to communicate and exchange with their friends, acquaintances or even with people they would like to know. In this paper, we propose to address hyperlocal communications as a transposition of the SNS paradigm to real life meetings and encounters. We also sketch our vision of Social Ambient Intelligence (SocAmI), in which user context knowledge is gathered and leveraged to ease and enhance the social communication experience in networking sites. We will rely on an analysis of the new usages of SNS, a definition of context-awareness, and the current trends that motivate our approach.

 

 

Leveraging Semantic Technologies towards Social Ambient Intelligence

 

• Authors: Adrien Joly, Pierre Maret, Fabien Bataille
• Publication: To appear in Context-Aware Mobile and Ubiquitous Computing for Enhanced Usability: Adaptive Technologies and Applications, 2008
• Abstract: These times, when the amount of information exponentially grows on the Internet, when most people can be connected at all times with powerful personal devices, we need to enhance, adapt and simplify access to information and communication with other people. The vision of ambient intelligence which is a relevant response to this need, brings many challenges in different areas such as context-awareness,  adaptive human-system interaction, privacy enforcement and social communications. We believe that ontologies and other semantic technologies can help meeting most of these challenges in a unified manner, as they are a bridge between meaningful (but fuzzy by nature) human knowledge and digital information systems. In this chapter, we will depict our vision of “Social Ambient Intelligence” based on the review of several uses of semantic technologies for context management, adaptive human-system interaction, privacy enforcement and social communications. Based on identified benefits and lacks, and on our experience, we will propose several research leads towards the realization of this vision.

 

A User Profile Ontology For Situation-Aware Social Networking (link)

 

• Authors: Johann Stan, Elöd Egyed-Zsigmond, Adrien Joly, Pierre Maret.
• Publication: In proceedings of Artificial Intelligence Techniques for Ambient Intelligence Workshop at ECAI 2008, Patras, Grece. 2008.
• Abstract: Today, more and more people possess mobile devices. This enables them to have access to a wide range of services, but also to be contacted anytime, anywhere, which can cause discomfort. Users should have full control on who can reach them and how, depending on their current situation: when at work, we wish a friend didn’t interrupted us, but when having a family dinner, we wish a call related to work didn’t occur. Even more, situation changes need to be detected in real-time, since preferences change a lot. We present in this paper an ontology-based user profile model, that allows users to have a situation-aware social network, by controlling how reachable they are for specific categories of people in a given situation.

 

 

An Adaptive and Extensible Web-based Interface System for Interactive Video Contents Browsing (link)

 

• Authors: Adrien Joly, Dian Tjondronegoro
• Publication: Advances in Systems, Computing Sciences and Software Engineering (Springer, 2007), proceedings of the the International Conference on Systems, Computing Sciences and Software Engineering (CISSE 2006) E-Conference.

• Abstract: With the growing popularity of mobile devices (including phones and portable media players) and coverage of Internet access, we tend to develop the need of consuming video content on the move. Some technologies already allow end-users to watch TV and listen to news podcasts or download music videos on their devices. However, such services are restricted to a provider's selection of pre-formatted and linear content streams. Hence, we propose a web-based interface system that supports interactive contents navigation, making it possible for end-users to “surf” on video content like they are used to on the Web. This system is extensible to any specific domain of video contents, any web-enabled platform, and to any browsing scheme. In this paper, we will explain the architecture and design of this system, propose an application for soccer videos and present the results of its user evaluation.

• Keywords: architecture, multimedia, content, browse, hypermedia, navigation, video, semantic, XML, pipeline

 

 

Delivering a Fully Interactive Mobile TV (link)

 

• Authors: Dian Tjondronegoro, Lei Wang & Adrien Joly
• Publication: International Journal of Web Information Systems, Emerald Group Publishing Limited, 2006, Pp 197-211

• Abstract: Affordable mobile devices with video playback function are rapidly growing in the market. Current wireless and third generation communication networks enable smoother and higher quality streaming video. With the support of these technologies, most participants in telecom value-added service chain are planning to shift their business focus to a more profitable and appealing area, mobile TV. Previous work that survey on users’ behavior while consuming mobile TV has indicated that users normally watch brief and casual contents, and not the full program. However, most of the current services adopt a “push” approach since users passively receiving pre-defined contents, rather than pulling the interesting topics and segments. In order to promote a more enjoyable and rewarding watching experience, this paper will propose a framework to support a fully interactive mobile TV. The main goal is to enable users to: 1) visually locate interesting topics across multiple genres (such as news, sports and entertainment); and 2) fully control the playback flow of the multimedia items while selecting the most interesting segments. A web-based system has been developed to implement and test the effectiveness of the proposed framework in a wireless and mobile setting.

• Keywords: Mobile TV, Multimedia indexing retrieval, Web-based interface, Interactive services

 

 

A Scalable and Extensible Segment-Event-Object based Sports Video Retrieval System (link)

 

• Authors: Dian Tjondronegoro, Yi-Ping Phoebe Chen, Adrien Joly
• Publication: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP), May 2008

• Abstract: Sport video data is growing rapidly as a result of the maturing digital technologies that support digital video capture, faster data processing, and large storage. However, (1) semi-automatic content extraction and annotation, (2) scalable indexing model, and (3) effective retrieval and browsing, still pose the most challenging problems for maximizing the usage of large video databases. This paper will present the findings from a comprehensive work that proposes a scalable and extensible sports video retrieval system with two major contributions in the area of sports video indexing and retrieval. First, is an extensible sports video indexing model that utilizes semi-schema-based indexing scheme on top of an Object-Relationship approach to support gradual content-extraction. Second, is a set of novel queries which are based on XQuery to generate dynamic and user-oriented summaries and event structures. The proposed sports video retrieval system has been fully implemented and populated with soccer, tennis, swimming, and diving video. The system has been evaluated against 20 users to demonstrate and confirm its feasibility and benefits. The experimental sports genres were specifically selected to represent the four main categories of sports domain: period-, set-point-, time (race)-, and performance- based sports. Thus, the proposed system should be generic and robust for all types of sports.

• Keywords: Video database system, sports video retrieval, automatic content extraction, indexing, XML, XQuery, MPEG-7, mobile video interaction