Martin Theobald, Jonathan Siddharth, Andreas Paepcke
SpotSigs: robust and efficient near duplicate detection in large web collections
SIGIR, 2008.
@inproceedings{SIGIR-2008-TheobaldSP, author = "Martin Theobald and Jonathan Siddharth and Andreas Paepcke", booktitle = "{Proceedings of the 31st International ACM SIGIR Conference on Research and Development in Information Retrieval}", doi = "10.1145/1390334.1390431", isbn = "978-1-60558-164-4", pages = "563--570", publisher = "{ACM}", title = "{SpotSigs: robust and efficient near duplicate detection in large web collections}", year = 2008, }