Abstract | ||
---|---|---|
We present an efficient method for approximate search in a combination of several metric spaces -- which are a generalization of low level image features -- using an inverted index. Our approximation gives very high recall with subsecond response time on a real data set of one million images extracted from Flickr. We further exploit the inverted index to improve efficiency of the query processing by combining our search in metric features with search in associated textual metadata. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1145/1571941.1572142 | SIGIR |
Keywords | Field | DocType |
approximate search,metric feature,unified inverted index,text retrieval,high recall,efficient image,efficient method,low level image feature,inverted index,metric space,million image,associated textual metadata,query processing,image features,ir,metric spaces,multimedia,approximation | Inverted index,Metadata,Information retrieval,Pattern recognition,Computer science,Feature (computer vision),Response time,Exploit,Artificial intelligence,Metric space,Recall,Text retrieval | Conference |
Citations | PageRank | References |
1 | 0.36 | 2 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jonathan Mamou | 1 | 527 | 28.72 |
Yosi Mass | 2 | 574 | 60.91 |
Michal Shmueli-Scheuer | 3 | 89 | 16.11 |
Benjamin Sznajder | 4 | 61 | 4.83 |