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

Kazuya Ueki, Takayuki Hori, Tetsunori Kobayashi

Research output: Contribution to conferencePaperpeer-review

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.

Original languageEnglish
Publication statusPublished - 2020
Event2019 TREC Video Retrieval Evaluation, TRECVID 2019 - Gaithersburg, United States
Duration: 2019 Nov 122019 Nov 13

Conference

Conference2019 TREC Video Retrieval Evaluation, TRECVID 2019
CountryUnited States
CityGaithersburg
Period19/11/1219/11/13

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Waseda meisei softbank at TRECVID 2019: Ad-hoc video search'. Together they form a unique fingerprint.

Cite this