Stable Hyper-pooling and Query Expansion for Event Detection

Matthijs Douze, Jerome Revaud, Cordelia Schmid, Herve Jegou; The IEEE International Conference on Computer Vision (ICCV), 2013, pp. 1825-1832

Abstract


This paper makes two complementary contributions to event retrieval in large collections of videos. First, we propose hyper-pooling strategies that encode the frame descriptors into a representation of the video sequence in a stable manner. Our best choices compare favorably with regular pooling techniques based on k-means quantization. Second, we introduce a technique to improve the ranking. It can be interpreted either as a query expansion method or as a similarity adaptation based on the local context of the query video descriptor. Experiments on public benchmarks show that our methods are complementary and improve event retrieval results, without sacrificing efficiency.

Related Material


[pdf]
[bibtex]
@InProceedings{Douze_2013_ICCV,
author = {Douze, Matthijs and Revaud, Jerome and Schmid, Cordelia and Jegou, Herve},
title = {Stable Hyper-pooling and Query Expansion for Event Detection},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}