Waseda meisei at TRECVID 2017: Ad-hoc video search

Kazuya Ueki; Koji Hirakawa; Kotaro Kikuchi; Tetsuji Ogawa; Tetsunori Kobayashi

Waseda meisei at TRECVID 2017: Ad-hoc video search

Kazuya Ueki^*, Koji Hirakawa, Kotaro Kikuchi, Tetsuji Ogawa, Tetsunori Kobayashi

^*Corresponding author for this work

School of Fundamental Science and Engineering

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

6 Citations (Scopus)

Abstract

The Waseda Meisei team participated in the TRECVID 2017 Ad-hoc Video Search (AVS) task [1]. For this year’s AVS task, we submitted both manually assisted and fully automatic runs. Our approach used the following processing steps: building a large semantic concept bank using pre-trained convolutional neural networks (CNNs) and support vector machines (SVMs), calculating each concept score for all test videos (IACC 3), manually or automatically extracting several search keywords based on the given query phrases, and combining the semantic concept scores to obtain the final search result. Our best manually assisted run achieved a mean average precision (mAP) of 21.6%, which ranked the highest among all the submitted runs. Our best fully automatic run achieved a mAP of 15.9%, which ranked second among all participants.

Original language	English
Publication status	Published - 2017
Event	2017 TREC Video Retrieval Evaluation, TRECVID 2017 - Gaithersburg, United States Duration: 2017 Nov 13 → 2017 Nov 15

Conference

Conference	2017 TREC Video Retrieval Evaluation, TRECVID 2017
Country/Territory	United States
City	Gaithersburg
Period	17/11/13 → 17/11/15

ASJC Scopus subject areas

Electrical and Electronic Engineering
Information Systems
Signal Processing

Cite this

@conference{5334d12622464466aeee8caa8fb2a1df,

title = "Waseda meisei at TRECVID 2017: Ad-hoc video search",

abstract = "The Waseda Meisei team participated in the TRECVID 2017 Ad-hoc Video Search (AVS) task [1]. For this year{\textquoteright}s AVS task, we submitted both manually assisted and fully automatic runs. Our approach used the following processing steps: building a large semantic concept bank using pre-trained convolutional neural networks (CNNs) and support vector machines (SVMs), calculating each concept score for all test videos (IACC 3), manually or automatically extracting several search keywords based on the given query phrases, and combining the semantic concept scores to obtain the final search result. Our best manually assisted run achieved a mean average precision (mAP) of 21.6%, which ranked the highest among all the submitted runs. Our best fully automatic run achieved a mAP of 15.9%, which ranked second among all participants.",

author = "Kazuya Ueki and Koji Hirakawa and Kotaro Kikuchi and Tetsuji Ogawa and Tetsunori Kobayashi",

note = "Funding Information: This work was partially supported by JSPS KAKENHI Grant Number 15K00249 and 17H01831. Publisher Copyright: Copyright {\textcopyright} 2017 TRECVID 2017.All rights reserved.; 2017 TREC Video Retrieval Evaluation, TRECVID 2017 ; Conference date: 13-11-2017 Through 15-11-2017",

year = "2017",

language = "English",

}

TY - CONF

T1 - Waseda meisei at TRECVID 2017

T2 - 2017 TREC Video Retrieval Evaluation, TRECVID 2017

AU - Ueki, Kazuya

AU - Hirakawa, Koji

AU - Kikuchi, Kotaro

AU - Ogawa, Tetsuji

AU - Kobayashi, Tetsunori

PY - 2017

Y1 - 2017

N2 - The Waseda Meisei team participated in the TRECVID 2017 Ad-hoc Video Search (AVS) task [1]. For this year’s AVS task, we submitted both manually assisted and fully automatic runs. Our approach used the following processing steps: building a large semantic concept bank using pre-trained convolutional neural networks (CNNs) and support vector machines (SVMs), calculating each concept score for all test videos (IACC 3), manually or automatically extracting several search keywords based on the given query phrases, and combining the semantic concept scores to obtain the final search result. Our best manually assisted run achieved a mean average precision (mAP) of 21.6%, which ranked the highest among all the submitted runs. Our best fully automatic run achieved a mAP of 15.9%, which ranked second among all participants.

AB - The Waseda Meisei team participated in the TRECVID 2017 Ad-hoc Video Search (AVS) task [1]. For this year’s AVS task, we submitted both manually assisted and fully automatic runs. Our approach used the following processing steps: building a large semantic concept bank using pre-trained convolutional neural networks (CNNs) and support vector machines (SVMs), calculating each concept score for all test videos (IACC 3), manually or automatically extracting several search keywords based on the given query phrases, and combining the semantic concept scores to obtain the final search result. Our best manually assisted run achieved a mean average precision (mAP) of 21.6%, which ranked the highest among all the submitted runs. Our best fully automatic run achieved a mAP of 15.9%, which ranked second among all participants.

UR - http://www.scopus.com/inward/record.url?scp=85086287190&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85086287190&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85086287190

Y2 - 13 November 2017 through 15 November 2017

ER -

Waseda meisei at TRECVID 2017: Ad-hoc video search

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this