講演抄録/キーワード |
講演名 |
2020-03-16 14:55
Egocentric Action Recognition on Noisy Videos ○Lijin Yang・Yifei Huang・Yusuke Sugano・Yoichi Sato(UTokyo) PRMU2019-73 |
抄録 |
(和) |
Egocentric videos in real-life setting (like vlogs on YouTube) are often flooded with outlier frames and content-irrelevant shots, which dramatically reduce the action recognition accuracy and efficiency. In this work, we proposed a Sampler-Evaluator mechanism that could cooperate with any existing action recognition models and select informative frames from noisy input videos for them. Experiments shows that with our Sampler-Evaluator modules we can increase the action recognition performance of the backbone model. |
(英) |
Egocentric videos in real-life setting (like vlogs on YouTube) are often flooded with outlier frames and content-irrelevant shots, which dramatically reduce the action recognition accuracy and efficiency. In this work, we proposed a Sampler-Evaluator mechanism that could cooperate with any existing action recognition models and select informative frames from noisy input videos for them. Experiments shows that with our Sampler-Evaluator modules we can increase the action recognition performance of the backbone model. |
キーワード |
(和) |
egocentric action recognition / frame selection / / / / / / |
(英) |
egocentric action recognition / frame selection / / / / / / |
文献情報 |
信学技報, vol. 119, no. 481, PRMU2019-73, pp. 45-50, 2020年3月. |
資料番号 |
PRMU2019-73 |
発行日 |
2020-03-09 (PRMU) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
PRMU2019-73 |