Generating diverse and representative image search results for landmarks

  title={Generating diverse and representative image search results for landmarks},
  author={Lyndon S. Kennedy and Mor Naaman},
Can we leverage the community-contributed collections of rich media on the web to automatically generate representative and diverse views of the world's landmarks? We use a combination of context- and content-based tools to generate representative sets of images for location-driven features and landmarks, a common search task. To do that, we using location and other metadata, as well as tags associated with images, and the images' visual features. We present an approach to extracting tags that… 

Figures and Tables from this paper

Visual summaries of popular landmarks from community photo collections

A novel data-driven algorithm that leverages online image repositories such as Flickr for automatically generating tourist maps and removes clutter from the representative image and applies non-photorealistic rendering techniques to generate a map icon for each landmark.

Finding representative and diverse community contributed images to create visual summaries of geographic areas

An automatic approach that uses community-contributed images to create representative and diverse visual summaries of specific geographic areas using a multimodal graph and introduces an edge-weighting mechanism for the fusion of heterogeneous modalities.

Generating Visual Summaries of Geographic Areas Using Community-Contributed Images

A novel approach for automatic visual summarization of a geographic area that exploits user-contributed images and related explicit and implicit metadata collected from popular content-sharing websites and presents a novel evaluation protocol, which does not require input of human annotators.

A hybrid approach for retrieving diverse social images of landmarks

A novel method that can produce a visual description of a landmark by choosing the most diverse pictures that best describe all the details of the queried location from community-contributed datasets is presented.

Mining Regional Representative Photos from Consumer-Generated Geotagged Photos

The results show the ability of the approach to mine regional representative photographs, and helps to understand how objects, scenes or events corresponding to the same given keywords are visually different and discover cultural differences depending on local regions over the world.

Mapping the world's photos

This work uses the spatial distribution of where people take photos to define a relational structure between the photos that are taken at popular places, and finds that visual and temporal features improve the ability to estimate the location of a photo, compared to using just textual features.

Not all tags are created equal: Learning flickr tag semantics for global annotation

The ability to automatically learn tag semantics by mining a global georeferenced image collection crawled from Flickr with the aim of improving an automatic annotation system is explored.

Topic models for image retrieval on large-scale databases

With the explosion of the number of images in personal and on-line collections, efficient techniques for navigating, indexing, labeling and searching images become more and more important. In this

Image clustering based on a shared nearest neighbors approach for tagged collections

A new method for extracting meaningful and representative clusters based on a shared nearest neighbors (SNN) approach that treats both content-based features and textual descriptions (tags) and some experimental results show that this approach extracts representative information of an image set.

Visual Discovery of Landmarks and their Details in Large-Scale Image Collections

This thesis presents the Hierarchical Iconoid Shift algorithm that, instead of a flat clustering, produces a hierarchy of clusters, where each cluster represents a building sub-structure, and proposes efficient parallel algorithms for performing this mode search.



Scene Summarization for Online Image Collections

This work proposes a solution to the problem of scene summarization by examining the distribution of images in the collection to select a set of canonical views to form the scene summary, using clustering techniques on visual features.

Combination of content analysis and context features for digital photograph retrieval.

This retrieval scenario, where a user is searching for photos of a known building or monument in a large shared collection, content-based techniques can offer a significant improvement over ranking based on context (specifically location) alone.

World explorer: visualizing aggregate data from unstructured text in geo-referenced collections

This work analyzes the tags associated with the geo-referenced Flickr images to generate aggregate knowledge in the form of "representative tags" for arbitrary areas in the world, and uses these tags to create a visualization tool, World Explorer, that can help expose the content of the data, using a map interface to display the derived tags and the original photo items.

Geographic location tags on digital images

An end-to-end system that capitalizes on geographic location tags for digital photographs, a lightweight travelogue-authoring tool that automatically creates appropriate context maps for a slideshow of location- tagged photographs, and an intuitive UI for browsing a massive location-tagged image database are described.

From Where to What: Metadata Sharing for Digital Photographs with Geographic Coordinates

The results show that the LOCALE system performs search tasks with surprising accuracy, even when searching for specific landmarks.

IGroup: presenting web image search results in semantic clusters

IGroup, a proposed image search engine addresses problems of browsing with web image search engines by presenting the result in semantic clusters, and shows significant improvement in such criteria.

How flickr helps us make sense of the world: context and content in community-contributed media collections

A location-tag-vision-based approach to retrieving images of geography-related landmarks and features from the Flickr dataset is demonstrated, suggesting that community-contributed media and annotation can enhance and improve access to multimedia resources - and the understanding of the world.

Towards automatic extraction of event and place semantics from flickr tags

An approach for extracting semantics of tags, unstructured text-labels assigned to resources on the Web, based on each tag's usage patterns, and shows that the Scale-structure Identification method outperforms the existing techniques.

Using context and similarity for face and location identification

New methods for determining image similarity are combined with analysis of automatically acquired contextual metadata to substantially improve the performance of face and place recognition algorithms, indicating the possibilities of a new context-aware paradigm for image analysis.

Hierarchical clustering of WWW image search results using visual, textual and link information

A hierarchical clustering method using visual, textual and link analysis to cluster the search results into different semantic clusters of image search results is proposed.