Adam Rae

Mining the web for points of interest

A point of interest (POI) is a focused geographic entity such as a landmark, a school, an historical building, or a business. Points of interest are the basis for most of the data supporting location-based applications. In this paper we propose to curate POIs from online sources by bootstrapping training data from Web snippets, seeded by POIs gathered from social media. This large corpus is used to train a sequential tagger to recognize mentions of POIs in text. Using Wikipedia data as the training data, we can identify POIs in free text with an accuracy that is 116% better than the state of the art POI identifier in terms of precision, and 50% better in terms of recall. We show that using Foursquare and Gowalla checkins as seeds to bootstrap training data from Web snippets, we can improve precision between 16% and 52%, and recall between 48% and 187% over the state-of-the-art. The name of a POI is not sufficient, as the POI must also be associated with a set of geographic coordinates. Our method increases the number of POIs that can be localized nearly three-fold, from 134 to 395 in a sample of 400, with a median localization accuracy of less than one kilometer.

Uncovering locally characterizing regions within geotagged data

We propose a novel algorithm for uncovering the colloquial boundaries of locally characterizing regions present in collections of labeled geospatial data. We address the problem by first modeling the data using scale-space theory, allowing us to represent it simultaneously across different scales as a family of increasingly smoothed density distributions. We then derive region boundaries by applying localized label weighting and image processing techniques to the scale-space representation of each label. Important insights into the data can be acquired by visualizing the shape and size of the resulting boundaries for each label at multiple scales. We demonstrate our technique operating at scale by discovering the boundaries of the most geospatially salient tags associated with a large collection of georeferenced photos from Flickr and compare our characterizing regions that emerge from the data with those produced by a recent technique from the research literature.

The Benchmark as a Research Catalyst: Charting the Progress of Geo-prediction for Social Multimedia

Benchmarks have the power to bring research communities together to focus on specific research challenges. They drive research forward by making it easier to systematically compare and contrast new solutions, and evaluate their performance with respect to the existing state of the art. In this chapter, we present a retrospective on the Placing Task, a yearly challenge offered by the MediaEval Multimedia Benchmark. The Placing Task, launched in 2010, is a benchmarking task that requires participants to develop algorithms that automatically predict the geolocation of social multimedia (videos and images). This chapter covers the editions of the Placing Task offered in 2010–2013, and also presents an outlook onto 2014. We present the formulation of the task and the task dataset for each year, tracing the design decisions that were made by the organizers, and how each year built on the previous year. Finally, we provide a summary of future directions and challenges for multimodal geolocation, and concluding remarks on how benchmarking has catalyzed research progress in the research area of geolocation prediction for social multimedia.

Exploring and browsing photos through characteristic geographic tag regions

We present a system that supports zoomable browsing and exploration of photos taken across the globe. Our system is based on a novel algorithm that automatically uncovers the colloquial boundaries of regions that are characteristic for individual tags used in a large collection of geo-referenced photos. We first model the data using scale-space theory, which allows us to represent it simultaneously across different scales as a family of increasingly smoothed density distributions, after which we derive the region boundaries by applying image analysis techniques to the scale-space representation of each tag. The interface visualizes the shape and size of the resulting boundaries for each tag along the dimensions of space and time across multiple scales, giving the user the ability to explore the world as patchwork of dynamic characterizing geographic tag regions and to browse through their associated photos.

GLOCAL: event-based retrieval of networked media

The idea of the European project GLOCAL is to use events as the central concept for search, organization and combination of multimedia content from various sources. For this purpose methods for event detection and event matching as well as media analysis are developed. Considered events range from private, over local, to global events.

State of the Geotag: where are we?

Assigning location information to online media has grown from a fringe activity to an automated process aided by supportive hardware and software. This has lead to increasing availability of geographic context for the picture, videos and audio users share on the web. Such data has allowed systems to search through, browse and analyse media according to location without being wholly dependant on expensive manual annotation. However, the current extent of much geographic metadata consists of describing a single pair of coordinates per item. There is difficulty in encoding the multiple locations pertinent to the content of an image, the location of the camera, as well as handling the multiple locations that may be associated with sections of video. Current media retrieval systems use geographic indexing to return results that are relevant to an area defined as within the radius of a point or an official bounding box. This ignores the complexity of canonical geographic boundaries, as well as the colloquial nature of many commonly-referred to geographic points and areas, highlighting the relationship between these two complementary geographies. By addressing these current limitations, future geographic multimedia retrieval systems will be able to better support user engagement with media.