MIC-TJU in MediaEval 2017 Emotional Impact of Movies Task

To predict the emotional impact and fear of movies, we propose a framework which employs four audio-visual features. In particular, we utilize the features extracted by the methods of motion keypoint trajectory and convolutional neural networks to depict the visual information, and extract a global and a local audio features to describe the audio cues. The early fusion strategy is employed to combine the vectors of these features. Then, the linear support vector regression and support vector machine are used to learn the affective models. The experimental results show that the combination of these features obtains promising performances.