论文信息 - THU-HCSI at MediaEval 2016: Emotional Impact of Movies Task

THU-HCSI at MediaEval 2016: Emotional Impact of Movies Task

In this paper we describe our team’s approach to MediaEval 2016 Challenge “Emotional Impact of Movies”. Except for the baseline features, we extract audio features and image features from video clips. We deploy Convolutional Neural Network (CNN) to extract image features and use OpenSMILE toolbox to extract audio ones. We also study multi-scale approach at different levels aiming at the continuous prediction task, using Long-short Term Memory (LSTM) and Bi-directional Long-short Term Memory (BLSTM) models. Fusion methods are also considered and discussed in this paper. The evaluation results show our approaches’ effectiveness.

Mingxing Xu | Zipeng Ye | Ye Ma

[1] Emmanuel Dellandréa,et al. The MediaEval 2016 Emotional Impact of Movies Task , 2016, MediaEval.

[2] Jürgen Schmidhuber,et al. Long Short-Term Memory , 1997, Neural Computation.

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

[4] Björn W. Schuller,et al. Recent developments in openSMILE, the munich open-source multimedia feature extractor , 2013, ACM Multimedia.

[5] Emmanuel Dellandréa,et al. LIRIS-ACCEDE: A Video Database for Affective Content Analysis , 2015, IEEE Transactions on Affective Computing.

[6] K. Scherer,et al. On the Acoustics of Emotion in Audio: What Speech, Music, and Sound have in Common , 2013, Front. Psychol..

[7] Emmanuel Dellandréa,et al. Deep learning vs. kernel methods: Performance for emotion prediction in videos , 2015, ACII.

[8] Jürgen Schmidhuber,et al. Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[9] Trevor Darrell,et al. Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[10] Björn W. Schuller,et al. The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing , 2016, IEEE Transactions on Affective Computing.

[11] Xinxing Li,et al. DBLSTM-based multi-scale fusion for dynamic emotion prediction in music , 2016, 2016 IEEE International Conference on Multimedia and Expo (ICME).