论文信息 - LIG at MediaEval 2015 Multimodal Person Discovery in Broadcast TV Task

LIG at MediaEval 2015 Multimodal Person Discovery in Broadcast TV Task

In this working notes paper the contribution of the LIG team (partnership between Univ. Grenoble Alpes and Ozyegin University) to the Multimodal Person Discovery in Broadcast TV task in MediaEval 2015 is presented. The task focused on unsupervised learning techniques. Two dierent approaches were submitted by the team. In the rst one, new features for face and speech modalities were tested. In the second one, an alternative way to calculate the distance between face tracks and speech segments is presented. It also had a competitive MAP score and was able to beat the baseline.

[1] Andrew Zisserman,et al. Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2] Georges Quénot,et al. Unsupervised Speaker Identification using Overlaid Texts in TV Broadcast , 2012, INTERSPEECH.

[3] Georges Quénot,et al. From Text Detection in Videos to Person Identification , 2012, 2012 IEEE International Conference on Multimedia and Expo.

[4] Geoffrey E. Hinton,et al. ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5] Patrick Kenny,et al. Front-End Factor Analysis for Speaker Verification , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[6] Claude Barras,et al. Multimodal Person Discovery in Broadcast TV at MediaEval 2016 , 2015, MediaEval.