Abstract
In this paper, we propose a new framework for global affective video content regression with five complementary audio-visual features. For the audio modality, we select the global audio feature eGeMAPS and two deep features SoundNet and VGGish. As for the visual modality, the key frames of original images and those of optical flow images are both used to extract VGG-19 features with finetuned models, in order to represent the original visual cues in conjunction with motion information. In the experiments, we perform the evaluations of selected audio and visual features on the dataset of Emotional Impact of Movies Task 2016 (EIMT16), and compare our results with those of competitive teams in EIMT16 and state-of-the-art method. The experimental results show that the fusion of five features can achieve better regression results in both arousal and valence dimensions, indicating the selected five features are complementary with each other in the audio-visual modalities. Furthermore, the proposed approach can achieve better regression results than the state-of-the-art method in both evaluation metrics of MSE and PCC in the arousal dimension and comparable MSE results in the valence dimension. Although our approach obtains slightly lower PCC result than the state-of-the-art method in the valence dimension, the fused feature vectors used in our framework have much lower dimensions with a total of 1752, only five thousandths of feature dimensions in the state-of-the-art method, largely bringing down the memory requirements and computational burden.
This work is supported by the National Natural Science Foundation of China under Grant Nos. 61801440 and 61631016, and the Fundamental Research Funds for the Central Universities under Grant Nos. 2018XNG1824 and YLSZ180226.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baveye, Y., Chamaret, C., Dellandréa, E., Chen, L.M.: Affective video content analysis: a multidisciplinary insight. IEEE Trans. Affect. Comput. 9(4), 396–409 (2018)
Baveye, Y., Dellandréa, E., Chamaret, C., Chen, L.M.: LIRIS-ACCEDE: a video database for affective content analysis. IEEE Trans. Affect. Comput. 6(1), 43–55 (2015)
Sjöberg, M., Baveye, Y., Wang, H.L., Quang, V.L., Ionescu, B., et al.: The MediaEval 2015 affective impact of movies task. In: MediaEval (2015)
Dellandréa, E., Chen, L.M., Baveye, Y., Sjöberg, M.V., Chamaret, C.: The MediaEval 2016 emotional impact of movies task. In: MediaEval (2016)
Chen, S.Z., Jin, Q.: RUC at MediaEval 2016 emotional impact of movies task: fusion of multimodal features. In: MediaEval (2016)
Liu, Y., Gu, Z.L., Zhang, Y., Liu, Y.: Mining emotional features of movies. In: MediaEval (2016)
Ma, Y., Ye, Z.P., Xu, M.X.: THU-HCSI at MediaEval 2016: emotional impact of movies task. In: MediaEval (2016)
Jan, A., Gaus, Y.F.B.A., Meng, H.Y., Zhang, F.: BUL in MediaEval 2016 emotional impact of movies task. In: MediaEval (2016)
Timoleon, A.T., Hadjileontiadis, L.J.: AUTH-SGP in MediaEval 2016 emotional impact of movies task. In: MediaEval (2016)
Yi, Y., Wang, H.L.: Multi-modal learning for affective content analysis in movies. Multimedia Tools Appl. 78(10), 13331–13350 (2019)
Eyben, F., Scherer, K.R., Schuller, B.W., Sundberg, J., Andre, E., et al.: The geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing. IEEE Trans. Affect. Comput. 7(2), 190–202 (2016)
Aytar, Y., Vondrick, C., Torralba, A.: SoundNet: learning sound representations from unlabeled video. In: Advances in Neural Information Processing Systems, pp. 892–900. Barcelona, Spain (2016)
Gemmeke, J.F., Ellis, D.P.W., Freedman, D., Jansen, A., Lawrence, W., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 776–780. New Orleans, USA (2017)
Hershey, S., Chaudhuri, S., Ellis, D.P.W., Gemmeke, J.F., Jansen, A., et al.: CNN architectures for large-scale audio classification. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 131–135. New Orleans, USA (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations. San Diego, USA (2015)
Crammer, K., Dekel, O., Keshet, J., Shalev-Shwartz, S., Singer, Y.: Online passive-aggressive algorithms. J. Mach. Learn. Res. 7(3), 551–585 (2006)
Efron, B., Hastie, T., Johnstone, I., Tibshirani, R., Ishwaran, H., et al.: Least angle regression. Ann. Stat. 32(2), 407–499 (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Guo, X., Zhong, W., Ye, L., Fang, L., Heng, Y., Zhang, Q. (2020). Global Affective Video Content Regression Based on Complementary Audio-Visual Features. In: Ro, Y., et al. MultiMedia Modeling. MMM 2020. Lecture Notes in Computer Science(), vol 11962. Springer, Cham. https://doi.org/10.1007/978-3-030-37734-2_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-37734-2_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37733-5
Online ISBN: 978-3-030-37734-2
eBook Packages: Computer ScienceComputer Science (R0)