Near-Duplicate Video Detection Based on an Approximate Similarity Self-Join Strategy

Abstract : The huge amount of redundant multimedia data, like video, has become a problem in terms of both space and copyright. Usually, the methods for identifying near-duplicate videos are neither adequate nor scalable to find pairs of similar videos. Similarity self-join operation could be an alternative to solve this problem in which all similar pairs of elements from a video dataset are retrieved. Nonetheless, methods for similarity self-join have poor performance when applied to high-dimensional data. In this work, we propose a new approximate method to compute similarity self-join in sub-quadratic time in order to solve the near-duplicate video detection problem. Our strategy is based on clustering techniques to find out groups of videos which are similar to each other.
Document type :
Conference papers
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-01305691
Contributor : Laurent Amsaleg <>
Submitted on : Monday, April 25, 2016 - 3:29:59 PM
Last modification on : Thursday, February 7, 2019 - 4:14:09 PM
Long-term archiving on : Tuesday, November 15, 2016 - 8:47:41 AM

File

v2.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01305691, version 1

Citation

Henrique Batista Da Silva, Zenilton Patrocino Jr., Guillaume Gravier, Laurent Amsaleg, Arnaldo de A. Araújo, et al.. Near-Duplicate Video Detection Based on an Approximate Similarity Self-Join Strategy. 14th International Workshop on Content-based Multimedia Indexing, Jun 2016, bucarest, Romania. ⟨hal-01305691⟩

Share

Metrics

Record views

1162

Files downloads

620