Skip to Main content Skip to Navigation
Conference papers

CLIPS and NII at TRECvid: Shot segmentation and feature extraction

Abstract : This paper presents the systems used by CLIPS- IMAG laboratory. We participated to shot seg- mentation and high-level extraction tasks. We fo- cus this year on High-Level Features Extraction task, based on key frames classification. We pro- pose an original and promising framework for in- corporating contextual information (from image content) into the concept detection process. The proposed method combines local and global clas- sifiers with stacking, using SVM. We handle topo- logic and semantic contexts in concept detection performance and proposed solutions to handle the large amount of dimensions involved in classified data.
Document type :
Conference papers
Complete list of metadata

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-00953918
Contributor : Marie-Christine Fauvet <>
Submitted on : Monday, March 3, 2014 - 2:36:13 PM
Last modification on : Wednesday, June 30, 2021 - 10:14:02 AM
Long-term archiving on: : Saturday, May 31, 2014 - 10:50:12 AM

File

clips-nii.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00953918, version 1

Collections

Citation

Stéphane Ayache, Georges Quénot, Jérôme Gensel, Shin'Ichi Satoh. CLIPS and NII at TRECvid: Shot segmentation and feature extraction. TREC Workshop on Video Retrieval Evaluation, 2005, Gaithersburg, MD, United States. ⟨hal-00953918⟩

Share

Metrics

Record views

338

Files downloads

147