Robust and efficient models for action recognition and localization

Dan Oneata 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Video interpretation and understanding is one of the long-term research goals in computer vision. Realistic videos such as movies present a variety of challenging machine learning problems, such as action classification/action retrieval, human tracking, human/object interaction classification, etc. Recently robust visual descriptors for video classification have been developed, and have shown that it is possible to learn visual classifiers in realistic difficult settings. However, in order to deploy visual recognition systems on large-scale in practice it becomes important to address the scalability of the techniques. The main goal is this thesis is to develop scalable methods for video content analysis (eg for ranking, or classification).
Complete list of metadatas

Cited literature [263 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01217362
Contributor : Abes Star <>
Submitted on : Monday, October 19, 2015 - 2:52:16 PM
Last modification on : Thursday, December 20, 2018 - 1:26:31 AM
Long-term archiving on : Wednesday, January 20, 2016 - 1:00:49 PM

File

ONEATA_2015_archivage.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01217362, version 1

Collections

Citation

Dan Oneata. Robust and efficient models for action recognition and localization. Computer Vision and Pattern Recognition [cs.CV]. Université Grenoble Alpes, 2015. English. ⟨NNT : 2015GREAM019⟩. ⟨tel-01217362⟩

Share

Metrics

Record views

4512

Files downloads

1758