Inf@TRECVID 2019: instance search task

En Yu, Wenhe Liu, Guoliang Kang, Xiaojun Chang, Jiande Sun, Alexander Hauptmann

Research output: Chapter in Book/Report/Conference proceedingConference PaperOther

Abstract

We participated in one of the two types of Instance Search task in TRECVID 2019: Fully Automatic Search, without any human intervention. Firstly, the specific person and action are searched separately, and then we re-rank the two sorts of search results by ranking the one type scores according to the other type, as well as the score fusion. And thus, three kinds of final instance search results are submitted. Specifically, for the person search, our baseline consists of face detection, alignment and face feature selection. And for the action search, we integrate person detection, person tracking and feature selection into a framework to get the final 3D features for all tracklets in video shots. The official evaluations showed that our best search result gets the 4th place in the Automatic search.

Original languageEnglish
Title of host publicationTREDVID 2019
EditorsGeorge Awad
Place of PublicationSaarbrücken/Wadern Germany
PublisherSchloss Dagstuhl
Number of pages4
Publication statusPublished - 2019
EventTREC Video Retrieval Evaluation 2019 - Gaithersburg, United States of America
Duration: 12 Nov 201913 Nov 2019
https://dblp.org/db/conf/trecvid/trecvid2019.html (Proceedings)
https://www-nlpir.nist.gov/projects/tv2019/schedule.html (Website)

Conference

ConferenceTREC Video Retrieval Evaluation 2019
Abbreviated titleTRECVID 2019
Country/TerritoryUnited States of America
CityGaithersburg
Period12/11/1913/11/19
Internet address

Cite this