WasedA at TRECVID 2016: Ad-hoc video search

Kazuya Ueki; Kotaro Kikuchi; Susumu Saito; Tetsunori Kobayashi

WasedA at TRECVID 2016: Ad-hoc video search

Kazuya Ueki^*, Kotaro Kikuchi, Susumu Saito, Tetsunori Kobayashi

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

4 Citations (Scopus)

Abstract

Waseda participated in the TRECVID 2016 Ad-hoc Video Search (AVS) task [1]. For the AVS task, we submitted four manually assisted runs. Our approach used the following processing steps: manually creating several search keywords based on the given query phrase, calculating a score for each concept using visual features, and combining the semantic concepts to obtain the final scores. Our best run achieved a mean Average Precision (mAP) of 17.7%. It was ranked the highest among all the runs submitted.

Original language	English
Publication status	Published - 2016
Event	2016 TREC Video Retrieval Evaluation, TRECVID 2016 - Gaithersburg, United States Duration: 2016 Nov 14 → 2016 Nov 16

Conference

Conference	2016 TREC Video Retrieval Evaluation, TRECVID 2016
Country/Territory	United States
City	Gaithersburg
Period	16/11/14 → 16/11/16

ASJC Scopus subject areas

Information Systems
Signal Processing
Electrical and Electronic Engineering

Cite this

@conference{58e54cec509a4d9d81289c46988e827e,

title = "WasedA at TRECVID 2016: Ad-hoc video search",

abstract = "Waseda participated in the TRECVID 2016 Ad-hoc Video Search (AVS) task [1]. For the AVS task, we submitted four manually assisted runs. Our approach used the following processing steps: manually creating several search keywords based on the given query phrase, calculating a score for each concept using visual features, and combining the semantic concepts to obtain the final scores. Our best run achieved a mean Average Precision (mAP) of 17.7%. It was ranked the highest among all the runs submitted.",

author = "Kazuya Ueki and Kotaro Kikuchi and Susumu Saito and Tetsunori Kobayashi",

note = "Funding Information: This work was partially supported by JSPS KAKENHI Grant Number 15K00249 and Waseda University Grant for Special Research Projects 2016A-026. Publisher Copyright: Copyright {\textcopyright} TRECVID 2016.All rights reserved.; 2016 TREC Video Retrieval Evaluation, TRECVID 2016 ; Conference date: 14-11-2016 Through 16-11-2016",

year = "2016",

language = "English",

}

TY - CONF

T1 - WasedA at TRECVID 2016

T2 - 2016 TREC Video Retrieval Evaluation, TRECVID 2016

AU - Ueki, Kazuya

AU - Kikuchi, Kotaro

AU - Saito, Susumu

AU - Kobayashi, Tetsunori

N1 - Funding Information: This work was partially supported by JSPS KAKENHI Grant Number 15K00249 and Waseda University Grant for Special Research Projects 2016A-026. Publisher Copyright: Copyright © TRECVID 2016.All rights reserved.

PY - 2016

Y1 - 2016

N2 - Waseda participated in the TRECVID 2016 Ad-hoc Video Search (AVS) task [1]. For the AVS task, we submitted four manually assisted runs. Our approach used the following processing steps: manually creating several search keywords based on the given query phrase, calculating a score for each concept using visual features, and combining the semantic concepts to obtain the final scores. Our best run achieved a mean Average Precision (mAP) of 17.7%. It was ranked the highest among all the runs submitted.

AB - Waseda participated in the TRECVID 2016 Ad-hoc Video Search (AVS) task [1]. For the AVS task, we submitted four manually assisted runs. Our approach used the following processing steps: manually creating several search keywords based on the given query phrase, calculating a score for each concept using visual features, and combining the semantic concepts to obtain the final scores. Our best run achieved a mean Average Precision (mAP) of 17.7%. It was ranked the highest among all the runs submitted.

UR - http://www.scopus.com/inward/record.url?scp=85085788276&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85085788276&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85085788276

Y2 - 14 November 2016 through 16 November 2016

ER -

WasedA at TRECVID 2016: Ad-hoc video search

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this