EURECOM@MediaEval 2017: Media Genre Inference for Predicting Media Interestingness

In this paper, we present EURECOM’s approach to address the MediaEval 2017 Predicting Media Interestingness Task. We developed models for both the image and video subtasks. In particular, we investigate the usage of media genre information (i.e., drama, horror, etc.) to predict interestingness. Our approach is related to the affective impact of media content and is shown to be effective in predicting interestingness for both video shots and key-frames.

[1]  Luc Van Gool,et al.  Video summarization by learning submodular mixtures of objectives , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[3]  Xiangyang Xue,et al.  Understanding and Predicting Interestingness of Videos , 2013, AAAI.

[4]  Tao Xiang,et al.  Interestingness Prediction by Robust Learning to Rank , 2014, ECCV.

[5]  Mohammad Soleymani,et al.  Ranking Images and Videos on Visual Interestingness by Visual Sentiment Features , 2016, MediaEval.

[6]  Mohammad Soleymani,et al.  Analyzing and Predicting GIF Interestingness , 2016, ACM Multimedia.

[7]  Kien A. Hua,et al.  Multi-view Manifold Learning for Media Interestingness Prediction , 2017, ICMR.

[8]  Vladimir Pavlovic,et al.  Sentiment Flow for Video Interestingness Prediction , 2014, HuEvent '14.

[9]  John R. Smith,et al.  Harnessing A.I. for Augmenting Creativity: Application to Movie Trailer Creation , 2017, ACM Multimedia.

[10]  Luc Van Gool,et al.  The Interestingness of Images , 2013, 2013 IEEE International Conference on Computer Vision.

[11]  Gabriel S. Simoes,et al.  Movie genre classification with Convolutional Neural Networks , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[12]  Mohammad Soleymani.  The Quest for Visual Interest , 2015, ACM Multimedia.

[13]  K. Sivaraman,et al.  MovieScope: Movie trailer classification using Deep Neural Networks , 2017 .

[14]  Antonio Torralba,et al.  SoundNet: Learning Sound Representations from Unlabeled Video , 2016, NIPS.