Circulant temporal encoding for video retrieval and temporal alignment

Matthijs Douze 1, 2 Jérôme Revaud 2 Jakob Verbeek 2 Hervé Jégou 3 Cordelia Schmid 2
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
3 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : We address the problem of specific video event retrieval. Given a query video of a specific event, eg. a concert of Madonna, the goal is to retrieve other videos of the same event that temporally overlap with the query. Our approach encodes the frame descriptors of a video to jointly represent their appearance and temporal order. It exploits the properties of circulant matrices to efficiently compare the videos in the frequency domain. This offers a significant gain in complexity and accurately localizes the matching parts of videos. The descriptors can be compressed in the frequency domain with a product quantizer adapted to complex numbers. In this case, video retrieval is performed without decompressing the descriptors. The second problem we consider is the temporal alignment of a set of videos. We exploit the matching confidence and an estimate of the temporal offset computed for all pairs of videos by our retrieval approach. Our robust algorithm aligns the videos on a global timeline by maximizing the set of temporally consistent matches. The global temporal alignment enables synchronous playback of the videos of a given scene.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.inria.fr/hal-01162603
Contributor : Thoth Team <>
Submitted on : Thursday, June 11, 2015 - 6:58:45 PM
Last modification on : Saturday, January 12, 2019 - 1:06:49 AM
Long-term archiving on : Tuesday, April 25, 2017 - 6:42:30 AM

File

paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01162603, version 1
  • ARXIV : 1506.02588

Citation

Matthijs Douze, Jérôme Revaud, Jakob Verbeek, Hervé Jégou, Cordelia Schmid. Circulant temporal encoding for video retrieval and temporal alignment. 2015. ⟨hal-01162603v1⟩

Share

Metrics

Record views

186

Files downloads

207