Scalable action detection in video collections

Abstract : This thesis proposes new methods for indexing video collections with varied content, such as cultural archives. We focus on human actions, which represent an important cultural aspect, together with sound, images and speech. Our main technical challenge is 'How to quickly detect and precisely localize human actions in a large video collection, when these actions are given as a query through example video clips?'. Thus, the difficulty of the task is due to criteria: quality of detection and search response time.
Complete list of metadatas

https://tel.archives-ouvertes.fr/tel-01466845
Contributor : Abes Star <>
Submitted on : Monday, February 13, 2017 - 6:05:06 PM
Last modification on : Saturday, December 21, 2019 - 4:20:01 AM
Long-term archiving on: Sunday, May 14, 2017 - 4:51:48 PM

File

TheseSTOIAN.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01466845, version 1

Collections

Citation

Andrei Stoian. Scalable action detection in video collections. Image Processing [eess.IV]. Conservatoire national des arts et metiers - CNAM, 2016. English. ⟨NNT : 2016CNAM1034⟩. ⟨tel-01466845⟩

Share

Metrics

Record views

369

Files downloads

137