A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is
In many search scenarios, users sometimes find unexpected, yet interesting and useful results, which make them curious; they experience serendipity. This curiosity encourages them to explore further. We developed an entity search system designed to support such an experience. The system explores the potential of entities extracted from two of the most popular sources of user-generated content -Wikipedia, a user-curated online encyclopedia, and Yahoo Answers, a more unconstrained question &doi:10.1145/2682914.2682919 fatcat:kbdmek75jrdctmzcz6luyoyihq
more »... ring forum -in promoting serendipitous search. The content of each data source is represented as a large network of entities, enriched with metadata about sentiment, writing quality, and topical category. A lazy random walk with restart is implemented to retrieve entities from the networks for a given entity query. This paper discusses our work, focusing on our experience in designing, developing, and evaluating such a system. We also discuss the challenges in developing large-scale systems that aim to drive curiosity in search.
Laere et al. 24.20% 51.49% 63.27% 85.62% 97.85% This work 25.04% 53.53% 75.16% 87.21% 99.01% 1 km 10 km 100 km 1000 km 10000 km Li et al.  0.21% 1.12% 2.71% 12.16% 79.45% Krippner et al ... 38.21 65.58 83.24 92.05 2.92 Table 8 : 8 Comparison of the optimal configuration of this paper and the submissions to the 2011 Placing Task, evaluated over the 5347 test videos for 2011. 21% Van ...doi:10.1016/j.ins.2013.02.045 fatcat:conaztnl3bfabisnco55givhya
The seventh edition of the Placing Task at MediaEval focuses on two challenges: (1) estimation-based placing, which addresses estimating the geographic location where a photo or video was taken, and (2) verification-based placing, which addresses verifying whether a photo or video was indeed taken at a pre-specified geographic location. Like the previous edition, we made the organizer baselines for both subtasks available as open source code, and published a live leaderboard that allows thedblp:conf/mediaeval/ChoiHLT16 fatcat:owjmtvj5azcetkvwcmxejpy4r4
more »... icipants to gain insights into the effectiveness of their approaches compared to the official baselines and in relation to each other at an early stage, before the actual run submissions are due.
Lecture Notes in Computer Science
We explore the task of determining the geographic location of photos on Flickr, using combined evidence from Naive Bayes classifiers that are trained at different spatial resolutions. In particular, we estimate the location of Flickr photos, based on their tags, at four different scales, ranging from a city-level granularity to fine-grained intra-city areas. Using Dempster-Shafer's evidence theory, we combine the output of the different classifiers into a single mass assignment. We demonstratedoi:10.1007/978-3-642-15951-0_32 fatcat:zosbgcsddradfbfil6u3njcsce
more »... xperimentally that the induced belief and plausibility measures are useful to determine whether there is sufficient evidence to classify the photo at a given granularity. Thus an adaptive method is obtained, by which photos are georeferenced at the most appropriate resolution.
The sixth edition of the Placing Task at MediaEval introduces two new sub-tasks: (1) locale-based placing, which emphasizes the need to move away from an evaluation purely based on latitude and longitude towards an entity-centered evaluation, and (2) mobility-based placing, which addresses predicting missing locations within a sequence of movements; the latter is a specific real-world use case that so far has received little attention within the research community. Two additional changes overdblp:conf/mediaeval/ChoiHLT15 fatcat:v3cokkvy4rgv7cmgqggzltrcju
more »... e previous years are the introduction of open source organizer baselines for both sub-tasks shortly after the official data release, and the implementation of a live leaderboard, which allows the participants to gain insights into the effectiveness of their approaches compared to the official baselines and in relation to each other at an early stage, before the actual run submissions are due.
We explore the task of automatically assigning geographic coordinates to photos on Flickr. Using an approach based on k-medoids clustering and Naive Bayes classification, we demonstrate that the task is feasible, although high accuracy can only be expected for a portion of all photos. Based on this observation, we stress the importance of adaptive approaches that estimate locations at different granularities for different photos.doi:10.1145/1722080.1722087 dblp:conf/gir/LaereSD10 fatcat:uvzfjepiofho5nji5w5dzeob3m
We present DEESSE , a tool that enables an exploratory and serendipitous exploration -at entity level, of the content of two different social media: Wikipedia, a user-curated online encyclopedia, and Yahoo Answers, a more unconstrained question/answering forum. DEESSE represents the content of each source as an entity network, which is further enriched with metadata about sentiment, writing quality, and topical category. Given a query entity, entity results are retrieved from the network bydoi:10.1145/2661829.2661853 dblp:conf/cikm/LaereBML14 fatcat:hcambp2myjbord4k2llajmzvbu
more »... mploying an algorithm based on a random walk with restart to the query. Following the emerging paradigm of composite retrieval, we organize the results into topically coherent bundles instead of showing them in a simple ranked list.
Place recommender systems are increasingly being used to find places of a given type that are close to a user-specified location. As it is important for these systems to use an up-to-date database with a wide coverage, there is a need for techniques that are capable of expanding place databases in an automated way. On the other hand, social media are a rich source of geographically distributed information. In this paper, we therefore propose an approach to discover new instances of a givendoi:10.1109/wi-iat.2012.19 dblp:conf/webi/CanneytSLD12 fatcat:z3srunxwovganjuubkrxegoyv4
more »... type by exploiting correlations between terms and locations in geotagged social media. For a variety of place types, our approach is able to find places which are not yet included in popular place databases such as Foursquare or Google Places.
Olivier Van Laere Olivier Van Laere received his M. Sc. degree in Computer Science in July 2004, and his M. ...doi:10.1007/s10115-011-0411-7 fatcat:4m5fgoenvvfw5ccwsqdvtxpssq
It shows Flickr pictures for user olivier@achterberg who is logged in on his desktop. As Olivier is interested in scuba diving, some pictures related to diving are shown. ... This is illustrated with the following rule for user 'olivier@achterberg'. ...doi:10.1109/mprv.2011.60 fatcat:7mhqeau4mfeppiymo7kzoxtsr4
When all access options in the upper limbs have been exhausted, an autogenous access in lower limb is a valuable alternative to arteriovenous grafts. We report our experience of transposition of the femoral vein (tFV). Methods: From June 1984 to June 2011, 70 patients underwent 72 tFV in two centers (Paris and Meknès) with the same technique. All patients had exhausted upper arm veins or had central vein obstructions. Patients were followed by serial duplex scanning. All complications weredoi:10.1016/j.jvs.2012.01.068 pmid:22575481 fatcat:2rzt4nz6p5cgjjypuliwbx7qbq
more »... ded and statistical analysis of patency was performed according to intention to treat using the life-table method. Results: The mean interval between initiation of dialysis and creation of the tFV was 10 years. The sex ratio was even (one female/one male). Mean age was 48 years (range, 1-84 years), and there were no postoperative infections. Duplex measurements in 33 patients indicated high-flow: mean ؍ 1529 ؎ 429 mL/min; range, 700-3000 mL/min. Two immediate failures were observed and four patients were lost to follow-up soon after the access creation. Ten patients (14%) experienced minor complications (hematoma, five; lymphocele, one; delayed wound healing, two; distal edema, two) and 30 patients (42%) experienced mild complications (femoral vein and outflow stenosis, 16 [treated by percutaneous transluminal angioplasty, 13, or polytetrafluoroethylene patch, three]; puncture site complications, three [ischemia, two; infection, one]; reversible thrombosis, three [two surgical and one percutaneous thrombectomy]; abandoned thrombosis, eight [11%] after a mean patency of 8.1 years). Thirteen patients (18%) experienced major complications necessitating fistula ligation (ischemic complications, five diabetic patients with peripheral arterial occlusive disease [one major amputation included] ; lower leg compartment syndrome, one; acute venous hypertension, two; secondary major edema, two; high-output cardiac failure, one; bleeding, two). All the patent accesses (59/72) were utilized for dialysis after a mean interval of 2 ؎ 1 months (range, 1-7 months) resulting in an 82% success rate. According to life-table analysis, the primary patency rates at 1 and 9 years were 91% ؎ 4% and 45% ؎ 11%, respectively. The secondary patency rates at 1 and 9 years were 84% ؎ 5% and 56% ؎ 9%, respectively. Conclusions: Femoral vein transposition in the lower limb is a valuable alternative to arteriovenous grafts in terms of infection and long-term patency. Secondary venous percutaneous angioplasties may be necessary. High flow rates are frequently observed and patient selection is essential to avoid ischemic complications. ( J Vasc Surg 2012;56:440-5.) From the Clinique Jouvenet, Paris a ; the CMC Ambroise Paré, Neuilly sur Seine b ; the Polyclinique Cornette de St Cyr, Meknès c ; and the Clinique Arago, Paris. d This study was made possible by the financial support of the Société Française de l'Abord Vasculaire (SFAV).
NAC = non-attenuation-corrected images Van Weehaeghe et al. BMC Cancer (2018) 18:253 pretherapy and 17.6 cm 3 posttherapy. ...doi:10.1186/s12885-018-4154-7 pmid:29506493 pmcid:PMC5836457 fatcat:qhwpgk5tc5hzpdaa5hwdg7achu
The last few years, we have witnessed an exponential growth in available content, much of which is user generated (e.g. pictures, videos, blogs, reviews, etc.). The downside of this overwhelming amount of content is that it becomes increasingly difficult for users to identify the content they really need, resulting into considerable research efforts concerning personalised search and content retrieval. On the other hand, this enormous amount of content raises new possibilities: existingdoi:10.1016/j.jnca.2009.12.008 fatcat:kvvrnqet6zel3ddct5hv6xpsui
more »... can be enriched using this content, provided that the content items used match the user's personal interests. Ideally, these interests should be obtained in an automatic, transparent way for an optimal user experience. In this paper two models representing user profiles are presented, both based on keywords and with the goal to enrich real-time communication services. The first model consists of a light-weight keyword tree which is very fast, while the second approach is based on a keyword ontology containing extra temporal relationships to capture more details of the user's behavior, however exhibiting lower performance. The profile models are supplemented with a set of algorithms, allowing to learn user interests and retrieving content from personal content repositories. In order to evaluate the performance, an enhanced instant messaging communication service was designed. Through simulations the two models are assessed in terms of real-time behavior and extensibility. User evaluations allow to estimate the added value of the approach taken. The experiments conducted indicate that the algorithms succeed in retrieving content matching the user's interests and both models exhibit a linear scaling behavior. The algorithms perform clearly better in finding content matching several user interests when benefiting from the extra temporal information in the ontology based model.
In this paper, we show how the large amount of geographically annotated data in social media can be used to complement existing place databases. After explaining our method, we illustrate how this approach can be used to discover new instances of a given semantic type, using London as a case study. In particular, for several place types, our method finds places in London that are not yet contained in the databases used by Foursquare, Google, LinkedGeoData and Geonames. Encouraged by thesedoi:10.1145/2442952.2442954 dblp:conf/gis/CanneytLSD12 fatcat:ujk6fjqeo5c4jp6ro3mwgqfhc4
more »... s, we briefly sketch how similar techniques could potentially be used to identify likely errors in existing databases, to estimate the spatial extent of places, to discover semantic relationships between place types, and to recommend tags to users who are uploading photos.
Laere, O (Van Laere, Olivier) [ 1 ] ; Schockaert, S (Schockaert, Steven) [ 2 ] ; Dhoedt, B (Dhoedt, Bart) [ 1 ] Source: JOURNAL OF WEB SEMANTICS Volume:16 Pages: 17-31 DOI: 10.1016/j.websem.2012.05.005 ... These correlations are then used to obtain geographic information in the sense of Email addresses: firstname.lastname@example.org (Olivier Van Laere), S.Schockaert@cs.cardiff.ac.uk (Steven Schockaert) ...doi:10.2139/ssrn.3198976 fatcat:jsprxuvngzdmliyzh6oiml2sum
« Previous Showing results 1 — 15 out of 266 results