WasedA at TRECVID 2015: Semantic indexing

Kazuya Ueki, Tetsunori Kobayashi

研究成果: Paper査読

1 被引用数 (Scopus)


Waseda participated in the TRECVID 2015 Semantic Indexing (SIN) task [6]. For the SIN task, our approach used the following processing pipelines: feature extraction using several deep convolutional neural networks (CNNs); classification of the presence or absence of a detection target by support vector machines (SVMs); and fusion of multiple score outputs. In order to improve the performance of semantic video indexing, we employed the following techniques: utilizing multiple evidences observed in each video and compressing them into a fixed-length vector; introducing gradient and motion features to CNNs; enriching variations of the training and the testing sets; and extracting features from several CNNs trained with various large-scale datasets. Through these techniques, our best run achieved a mean Average Precision (mAP) of 30.9%. This was ranked 2nd among all the participants.

出版ステータスPublished - 2015
イベント2015 TREC Video Retrieval Evaluation, TRECVID 2015 - Gaithersburg, United States
継続期間: 2015 11月 162015 11月 18


Conference2015 TREC Video Retrieval Evaluation, TRECVID 2015
国/地域United States

ASJC Scopus subject areas

  • 情報システム
  • 電子工学および電気工学
  • 信号処理


「WasedA at TRECVID 2015: Semantic indexing」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。