Stable Hyper-pooling and Query Expansion for Event Detection

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

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.