• Publications
  • Influence
Sensing Trending Topics in Twitter
TLDR
We compare six topic detection methods on three Twitter datasets related to major events, which differ in their time scale and topic churn rate. Expand
  • 326
  • 39
  • PDF
Social Event Detection at MediaEval 2012: Challenges, Dataset and Evaluation
TLDR
This paper provides an overview of the Social Event Detection (SED) task, which is organized as part of the MediaEval 2012 benchmarking activity and examines how social events can be detected by automatically analyzing social multimedia content. Expand
  • 143
  • 21
  • PDF
Community detection in Social Media
TLDR
The proposed survey discusses the topic of community detection in the context of Social Media. Expand
  • 456
  • 16
  • PDF
Temporal Video Segmentation to Scenes Using High-Level Audiovisual Features
TLDR
In this paper, a novel approach to video temporal decomposition into semantic units, termed scenes, is presented. Expand
  • 92
  • 13
  • PDF
A soft frequent pattern mining approach for textual topic detection
TLDR
We treat the topic detection problem as a Frequent Pattern Mining problem and propose a novel algorithm for "soft" FrequentPattern Mining. Expand
  • 35
  • 11
  • PDF
Cluster-Based Landmark and Event Detection for Tagged Photo Collections
TLDR
An image analysis scheme can automate the detection of landmarks and events in large image collections, significantly improving the content-consumption experience. Expand
  • 151
  • 9
An ontology approach to object-based image retrieval
TLDR
In this paper, an image retrieval methodology suited for search in large collections of heterogeneous images is presented. Expand
  • 209
  • 8
  • PDF
Towards content-oriented patent document processing
TLDR
We introduce a content representation schema for patent documentation and sketch the design of techniques that facilitate the integration of this schema into the patent processing cycle. Expand
  • 94
  • 7
Video object segmentation using Bayes-based temporal tracking and trajectory-based region merging
TLDR
A novel unsupervised video object segmentation algorithm is presented, aiming to segment a video sequence to objects: spatiotemporal regions representing a meaningful part of the sequence. Expand
  • 75
  • 7
  • PDF
Semantic Annotation of Images and Videos for Multimedia Analysis
TLDR
M-OntoMat-Annotizer allows for linking low level MPEG-7 visual descriptions to conventional Semantic Web ontologies and annotations allowing for new kinds of multimedia content analysis. Expand
  • 238
  • 6
  • PDF