A Multi-Task Neural Approach for Emotion Attribution, Classification, and Summarization

@article{Tu2020AMN,
  title={A Multi-Task Neural Approach for Emotion Attribution, Classification, and Summarization},
  author={Guoyun Tu and Yanwei Fu and Boyang Li and Jiarui Gao and Yu-Gang Jiang and X. Xue},
  journal={IEEE Transactions on Multimedia},
  year={2020},
  volume={22},
  pages={148-159}
}
Emotional content is a crucial ingredient in user-generated videos. However, the sparsity of emotional expressions in the videos poses an obstacle to visual emotion analysis. In this paper, we propose a new neural approach, Bi-stream Emotion Attribution-Classification Network (BEAC-Net), to solve three related emotion analysis tasks: emotion recognition, emotion attribution, and emotion-oriented summarization, in a single integrated framework. BEAC-Net has two major constituents, an attribution… Expand
3 Citations
An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos
  • 8
  • Highly Influenced
  • PDF

References

SHOWING 1-10 OF 76 REFERENCES
Frame-Transformer Emotion Classification Network
  • 8
  • PDF
Heterogeneous Knowledge Transfer in Video Emotion Recognition, Attribution and Summarization
  • 51
  • PDF
Multimodal Multi-task Learning for Dimensional and Continuous Emotion Recognition
  • 65
A comprehensive study on mid-level representation and ensemble learning for emotional analysis of video material
  • 17
  • PDF
Combining modality specific deep neural networks for emotion recognition in video
  • 270
  • PDF
Video Emotion Recognition with Transferred Deep Feature Encodings
  • 32
  • PDF
Predicting Emotions in User-Generated Videos
  • 78
  • PDF
LIRIS-ACCEDE: A Video Database for Affective Content Analysis
  • 151
  • PDF
Deep Multimodal Learning for Affective Analysis and Retrieval
  • 78
  • PDF
...
1
2
3
4
5
...