%0 Conference Paper %1 Taneva:2010:GRP:1718487.1718541 %A Taneva, Bilyana %A Kacimi, Mouna %A Weikum, Gerhard %B Proceedings of the third ACM international conference on Web search and data mining %C New York, NY, USA %D 2010 %I ACM %K image namedentities %P 431--440 %R 10.1145/1718487.1718541 %T Gathering and ranking photos of named entities with high precision, high recall, and diversity %U http://doi.acm.org/10.1145/1718487.1718541 %X Knowledge-sharing communities like Wikipedia and automated extraction methods like those of DBpedia enable the construction of large machine-processible knowledge bases with relational facts about entities. These endeavors lack multimodal data like photos and videos of people and places. While photos of famous entities are abundant on the Internet, they are much harder to retrieve for less popular entities such as notable computer scientists or regionally interesting churches. Querying the entity names in image search engines yields large candidate lists, but they often have low precision and unsatisfactory recall.</p> <p>Our goal is to populate a knowledge base with photos of named entities, with high precision, high recall, and diversity of photos for a given entity. We harness relational facts about entities for generating expanded queries to retrieve different candidate lists from image search engines. We use a weighted voting method to determine better rankings of an entity's photos. Appropriate weights are dependent on the type of entity (e.g., scientist vs. politician) and automatically computed from a small set of training entities. We also exploit visual similarity measures based on SIFT features, for higher diversity in the final rankings. Our experiments with photos of persons and landmarks show significant improvements of ranking measures like MAP and NDCG, and also for diversity-aware ranking. %@ 978-1-60558-889-6

@inproceedings{Taneva:2010:GRP:1718487.1718541, abstract = {Knowledge-sharing communities like Wikipedia and automated extraction methods like those of DBpedia enable the construction of large machine-processible knowledge bases with relational facts about entities. These endeavors lack multimodal data like photos and videos of people and places. While photos of famous entities are abundant on the Internet, they are much harder to retrieve for less popular entities such as notable computer scientists or regionally interesting churches. Querying the entity names in image search engines yields large candidate lists, but they often have low precision and unsatisfactory recall.</p> <p>Our goal is to populate a knowledge base with photos of named entities, with high precision, high recall, and diversity of photos for a given entity. We harness relational facts about entities for generating expanded queries to retrieve different candidate lists from image search engines. We use a weighted voting method to determine better rankings of an entity's photos. Appropriate weights are dependent on the type of entity (e.g., scientist vs. politician) and automatically computed from a small set of training entities. We also exploit visual similarity measures based on SIFT features, for higher diversity in the final rankings. Our experiments with photos of persons and landmarks show significant improvements of ranking measures like MAP and NDCG, and also for diversity-aware ranking.}, acmid = {1718541}, added-at = {2011-07-17T21:41:15.000+0200}, address = {New York, NY, USA}, author = {Taneva, Bilyana and Kacimi, Mouna and Weikum, Gerhard}, biburl = {https://www.bibsonomy.org/bibtex/2833e3017a01d6e74cef02b884e829f32/jimregan}, booktitle = {Proceedings of the third ACM international conference on Web search and data mining}, description = {Gathering and ranking photos of named entities with high precision, high recall, and diversity}, doi = {10.1145/1718487.1718541}, interhash = {e745e0a11ce0c33022bf631a8a88b922}, intrahash = {833e3017a01d6e74cef02b884e829f32}, isbn = {978-1-60558-889-6}, keywords = {image namedentities}, location = {New York, New York, USA}, numpages = {10}, pages = {431--440}, publisher = {ACM}, series = {WSDM '10}, timestamp = {2011-07-17T21:41:16.000+0200}, title = {Gathering and ranking photos of named entities with high precision, high recall, and diversity}, url = {http://doi.acm.org/10.1145/1718487.1718541}, year = 2010 }