[SFB15] Scalable action localization with kernel-space hashing

Conférence Internationale avec comité de lecture : IEEE International Conference on Image Processing (ICIP), September 2015, pp.257-261, Quebec, Canada, (DOI: 10.1109/ICIP.2015.7350799)

Mots clés: Action localization, query-by-detector, LSH, hyperplane queries, kernel indexing

Résumé: To detect and locate complex human actions in video, one trains a detector for each target class and applies it to the video content. This approach can scale to large video databases if the application of the detector can be made sublinear in the size of the database. Sublinear retrieval methods have been successfully explored for query-by-example but few were devised for these more challenging queries by detector. We put forward here a novel approximate search method that relies on LSH to support query-by-detector. We evaluate our method on a recent large action localization dataset and show it has significantly better efficiency than linear search.

Equipe: vertigo
Collaboration: LaBRI


@inproceedings {
title="{Scalable action localization with kernel-space hashing}",
author=" A. Stoian and M. Ferecatu and J. Benois-Pineau and M. Crucianu ",
booktitle="{ IEEE International Conference on Image Processing (ICIP)}",
address="Quebec, Canada",