Sorry, you need to enable JavaScript to visit this website.

TIME-LAG AWARE MULTI-MODAL VARIATIONAL AUTOENCODER USING BASEBALL VIDEOS AND TWEETS FOR PREDICTION OF IMPORTANT SCENES

Citation Author(s):
Kaito Hirasawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
Submitted by:
Kaito Hirasawa
Last updated:
2 October 2021 - 12:28pm
Document Type:
Poster
Document Year:
2021
Event:
Presenters:
Kaito Hirasawa
Paper Code:
1695
 

A novel method based on time-lag aware multi-modal variational autoencoder for prediction of important scenes (Tl-MVAE-PIS) using baseball videos and tweets posted on Twitter is presented in this paper. This paper has the following two technical contributions. First, to effectively use heterogeneous data for the prediction of important scenes, we transform textual, visual and audio features obtained from tweets and videos to the latent features. Then Tl-MVAE-PIS can flexibly express the relationships between them in the constructed latent space. Second, since there are time-lags between tweets and the corresponding multiple previous events, Tl-MVAE-PIS considers such time-lags in their relationship estimation for successfully deriving their latent features. Therefore, these two contributions enable accurate important scene prediction. Results of experiments using actual baseball videos and their corresponding tweets show the effectiveness of Tl-MVAE-PIS.

up
0 users have voted: