Papers by Mathilde Sahuguet
Proceedings of the ACM International Conference on Multimedia - MM '14, 2014
This paper introduces a framework for establishing links between related media fragments within a... more This paper introduces a framework for establishing links between related media fragments within a collection of videos. A set of analysis techniques is applied for extracting information from different types of data. Visual-based shot and scene segmentation is performed for defining media fragments at different granularity levels, while visual cues are detected from keyframes of the video via concept detection and optical character recognition (OCR). Keyword extraction is applied on textual data such as the output of OCR, subtitles and metadata. This set of results is used for the automatic identification and linking of related media fragments. The proposed framework exhibited competitive performance in the Video Hyperlinking sub-task of MediaEval 2013, indicating that video scene segmentation can provide more meaningful segments, compared to other decomposition methods, for hyperlinking purposes.
Proceedings of International Conference on Multimedia Retrieval - ICMR '14, 2014
Currently, popular search engines retrieve documents on the basis of text information. However, i... more Currently, popular search engines retrieve documents on the basis of text information. However, integrating the visual information with the text-based search for video and image retrieval is still a hot research topic. In this paper, we propose and evaluate a video search framework based on using visual information to enrich the classic text-based search for video retrieval. The framework extends conventional text-based search by fusing together text and visual scores, obtained from video subtitles (or automatic speech recognition) and visual concept detectors respectively. We attempt to overcome the so called problem of semantic gap by automatically mapping query text to semantic concepts. With the proposed framework, we endeavor to show experimentally, on a set of real world scenarios, that visual cues can effectively contribute to the quality improvement of video retrieval. Experimental results show that mapping text-based queries to visual concepts improves the performance of the search system. Moreover, when appropriately selecting the relevant visual concepts for a query, a very significant improvement of the system's performance is achieved.
Linking text and visual concepts semantically for cross modal multimedia search
2014 IEEE International Conference on Image Processing (ICIP), 2014
Socially motivated multimedia topic timeline summarization
Proceedings of the 2nd international workshop on Socially-aware multimedia - SAM '13, 2013
ABSTRACT As the amount of social media shared on the Internet grows increasingly, it becomes poss... more ABSTRACT As the amount of social media shared on the Internet grows increasingly, it becomes possible to explore a topic with a novel, people based viewpoint. Contrasting with traditional man-made topic summarization which provide the personal view of its author, we want to focus on public reaction to events. To this end, we propose an approach to automatically generate a timeline of popular events related to a given topic. Time segments of interest are extracted from Google Trends results using a simple statistical approach. Each event, relevant to the specified topic, is illustrated on a timeline by videos mined from social media sharing platforms that gives context to the events and offers an overview of what has caught people's attention. We report the results provided by our approach for automatically illustrating the popular moments of four celebrities.
Mining the Web for Multimedia-Based Enriching
Lecture Notes in Computer Science, 2014
This paper aims at presenting the results of LinkedTV's first participation to the Search and Hyp... more This paper aims at presenting the results of LinkedTV's first participation to the Search and Hyperlinking task at Medi-aEval challenge 2013. We used textual information, transcripts, subtitles and metadata, and we tested their combination with automatically detected visual concepts. Hence, we submitted various runs to compare diverse approaches and see the improvement when adding visual information.
Event-based Summarization for Media Hyperlinking
Uploads
Papers by Mathilde Sahuguet