Multimedia information seeking through search and hyperlinking

Abstract

Searching for relevant webpages and following hyperlinks to related content is a widely accepted and effective approach to information seeking on the textual web. Existing work on multimedia information retrieval has focused on search for individual relevant items or on content linking without specific attention to search results. We describe our research exploring integrated multimodal search and hyperlinking for multimedia data. Our investigation is based on the MediaEval 2012 Search and Hyperlinking task. This includes a known-item search task using the Blip10000 internet video collection, where automatically created hyperlinks link each relevant item to related items within the collection. The search test queries and link assessment for this task was generated using the Amazon Mechanical Turk crowdsourcing platform. Our investigation examines a range of alternative methods which seek to address the challenges of search and hyperlinking using multimodal approaches. The results of our experiments are used to propose a research agenda for developing effective techniques for search and hyperlinking of multimedia content.

Linking Multimedia Content for Efficient News Browsing

“…By following links (that can be seen as user-independent recommendations), the user is able to navigate in an informed way, choosing his next step among a limited set of links that are related to the news item he is currently viewing [4]. When carefully cra ed, those links can provide a highly navigable structure, as evidenced in a number of application domains [16], including news [11].…”

“…Navigable graphs allow for interesting applications, such as connecting the dots between two arbitrary pieces of information [17]. In the absence of pre-de ned segments acting as the source of the links-the so-called anchors in [4]-, there are two main algorithms to create graphs that connect documents with hyperlinks: K nearest neighbors (K-NN) and E nearest neighbors (E-NN) graphs. Both consist in creating links between related elements, called (nearest) neighbors, in a collection, relying on a content-based distance function that measures how similar two documents are.…”

Shaping-Up Multimedia Analytics: Needs and Expectations of Media Professionals

“…Evaluations on video hyperlinking over the past few years, e.g., [5], are typically first step in this direction. Clearly, analytics cannot satisfy itself of documents taken regardless of the collection.…”

Exploiting Multimodality in Video Hyperlinking to Improve Target Diversity

“…The automatic generation of hyperlinks within video collections recently became a major subject, in particular via evaluation benchmarks within MediaEval and TRECVid [9,8,18]. The key idea is to create hyperlinks between video segments within a collection, enriching a set of anchors that represent interesting entry points in the collection.…”