Skip to Main content Skip to Navigation
Conference papers

Scalable action localization with kernel-space hashing

Abstract : 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.
Complete list of metadata
Contributor : Jenny Benois-Pineau <>
Submitted on : Monday, January 16, 2017 - 6:18:09 PM
Last modification on : Monday, September 7, 2020 - 12:10:03 PM



Andrei Stoian, Marin Ferecatu, Jenny Benois-Pineau, Michel Crucianu. Scalable action localization with kernel-space hashing. Image Processing (ICIP), 2015 IEEE International Conference on, Sep 2015, Québec, Canada. pp.257-261, ⟨10.1109/ICIP.2015.7350799⟩. ⟨hal-01436944⟩



Record views