Searching with expectations

18 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Product Quantization for Nearest Neighbor Search (2011, background): “It is also related to the work [2] on source coding for nearest neighbor search.”
The Faiss Library (2024, unknown): “The offsets on that direction are then discretized into buckets where the database vectors are stored.”
Optimized Product Quantization (2014, methodology): “A similar method was also concurrently proposed in [33].”
A Survey on Learning to Hash (2016, methodology): “(1) Principal component hashing [98] uses the principal direction to formulate the hash function; (2) Searching with expectations [123] and transform coding [9] that transforms the data”
Searching in one billion vectors: Re-rank with source coding (2011, unknown): “…outperformed in terms of the trade-off between memory usage and accuracy by recent meth-ods that cast high dimensional indexing to a source coding problem [11, 5, 6], in particular the product quantization-based method of [5] exhibits impressive results for large scale image search [6].”