Detection of Important Scenes in Baseball Videos via a Time-Lag-Aware Multimodal Variational Autoencoder
A new method for the detection of important scenes in baseball videos via a time-lag-aware multimodal variational autoencoder (Tl-MVAE) is presented in this paper. Tl-MVAE estimates latent features calculated from tweet, video, and audio features extracted from tweets and videos. Then, important sce...
Main Authors: | Kaito Hirasawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/6/2045 |
Similar Items
-
Time-Lag Aware Latent Variable Model for Prediction of Important Scenes Using Baseball Videos and Tweets
by: Kaito Hirasawa, et al.
Published: (2022-03-01) -
Favorite Video Classification Based on Multimodal Bidirectional LSTM
by: Takahiro Ogawa, et al.
Published: (2018-01-01) -
Cell Scene Division and Visualization Based on Autoencoder and K-Means Algorithm
by: Jun Zeng, et al.
Published: (2019-01-01) -
Proposing Multimodal Integration Model Using LSTM and Autoencoder
by: Wataru Noguchi, et al.
Published: (2016-12-01) -
Multimodal Shot Prediction Based on Spatial-Temporal Interaction between Players in Soccer Videos
by: Ryota Goka, et al.
Published: (2024-06-01)