ARTEMIS at TRECVID 2013: Instance search task

Andrei Bursuc, Titus Zaharia

Research output: Contribution to conferencePaperpeer-review

Abstract

This paper describes the approach proposed by the ARTEMIS team at TRECVID 2013, Instance Search (INS) task. The method is based on the Bag-of-Words representation obtained from uniform sampling of the frames of the videos. We propose two types of shot descriptors: one relying on a single representative frame for each video shot and another one collecting visual descriptors from multiple frames of the video clips.

Original languageEnglish
Publication statusPublished - 1 Jan 2013
Externally publishedYes
Event2013 TREC Video Retrieval Evaluation, TRECVID 2013 - Gaithersburg, United States
Duration: 20 Nov 201322 Nov 2013

Conference

Conference2013 TREC Video Retrieval Evaluation, TRECVID 2013
Country/TerritoryUnited States
CityGaithersburg
Period20/11/1322/11/13

Fingerprint

Dive into the research topics of 'ARTEMIS at TRECVID 2013: Instance search task'. Together they form a unique fingerprint.

Cite this