Waseda meisei softbank at TRECVID 2019: Ad-hoc video search

Kazuya Ueki; Takayuki Hori; Tetsunori Kobayashi

Waseda meisei softbank at TRECVID 2019: Ad-hoc video search

Kazuya Ueki^*, Takayuki Hori, Tetsunori Kobayashi

^*この研究の対応する著者

基幹理工学部

研究成果: Paper › 査読

3 被引用数 (Scopus)

抄録

The Waseda Meisei SoftBank team participated in the TRECVID 2019 Ad-hoc Video Search (AVS) task [1]. For this year's AVS task, we submitted both manually assisted and fully automatic runs. Our approach consisted of concept-based video retrieval for manually assisted runs and visual-semantic embedding for fully automatic runs. Our best manually assisted run achieved a mean average precision (mAP) of 15.2%, which ranked the highest among all the manually assisted systems. Our fully automatic run achieved an mAP of 12.3%, which ranked third among all participants.

本文言語	English
出版ステータス	Published - 2020
イベント	2019 TREC Video Retrieval Evaluation, TRECVID 2019 - Gaithersburg, United States 継続期間: 2019 11月 12 → 2019 11月 13

Conference

Conference	2019 TREC Video Retrieval Evaluation, TRECVID 2019
国/地域	United States
City	Gaithersburg
Period	19/11/12 → 19/11/13

ASJC Scopus subject areas

情報システム
信号処理
電子工学および電気工学

他のファイルとリンク

引用スタイル

@conference{8691caad3eb44df7b5fb1ee7c0a93251,

title = "Waseda meisei softbank at TRECVID 2019: Ad-hoc video search",

abstract = "The Waseda Meisei SoftBank team participated in the TRECVID 2019 Ad-hoc Video Search (AVS) task [1]. For this year's AVS task, we submitted both manually assisted and fully automatic runs. Our approach consisted of concept-based video retrieval for manually assisted runs and visual-semantic embedding for fully automatic runs. Our best manually assisted run achieved a mean average precision (mAP) of 15.2%, which ranked the highest among all the manually assisted systems. Our fully automatic run achieved an mAP of 12.3%, which ranked third among all participants.",

author = "Kazuya Ueki and Takayuki Hori and Tetsunori Kobayashi",

note = "Funding Information: This work was partially supported by JSPS KAKENHI Grant Number 17H01831 and 18K11362, and Kayamori Foundation of Informational Science Advancement. Publisher Copyright: Copyright {\textcopyright} TRECVID 2019.All rights reserved.; 2019 TREC Video Retrieval Evaluation, TRECVID 2019 ; Conference date: 12-11-2019 Through 13-11-2019",

year = "2020",

language = "English",

}

TY - CONF

T1 - Waseda meisei softbank at TRECVID 2019

T2 - 2019 TREC Video Retrieval Evaluation, TRECVID 2019

AU - Ueki, Kazuya

AU - Hori, Takayuki

AU - Kobayashi, Tetsunori

N1 - Funding Information: This work was partially supported by JSPS KAKENHI Grant Number 17H01831 and 18K11362, and Kayamori Foundation of Informational Science Advancement. Publisher Copyright: Copyright © TRECVID 2019.All rights reserved.

PY - 2020

Y1 - 2020

N2 - The Waseda Meisei SoftBank team participated in the TRECVID 2019 Ad-hoc Video Search (AVS) task [1]. For this year's AVS task, we submitted both manually assisted and fully automatic runs. Our approach consisted of concept-based video retrieval for manually assisted runs and visual-semantic embedding for fully automatic runs. Our best manually assisted run achieved a mean average precision (mAP) of 15.2%, which ranked the highest among all the manually assisted systems. Our fully automatic run achieved an mAP of 12.3%, which ranked third among all participants.

AB - The Waseda Meisei SoftBank team participated in the TRECVID 2019 Ad-hoc Video Search (AVS) task [1]. For this year's AVS task, we submitted both manually assisted and fully automatic runs. Our approach consisted of concept-based video retrieval for manually assisted runs and visual-semantic embedding for fully automatic runs. Our best manually assisted run achieved a mean average precision (mAP) of 15.2%, which ranked the highest among all the manually assisted systems. Our fully automatic run achieved an mAP of 12.3%, which ranked third among all participants.

UR - http://www.scopus.com/inward/record.url?scp=85084950917&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85084950917&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85084950917

Y2 - 12 November 2019 through 13 November 2019

ER -

Waseda meisei softbank at TRECVID 2019: Ad-hoc video search

抄録

Conference

ASJC Scopus subject areas

他のファイルとリンク

フィンガープリント

引用スタイル