Learning Emotion Representations from Verbal and Nonverbal Communication

Sitao Zhang, Yimu Pan, James Z. Wang
The Pennsylvania State University, USA

Emotion understanding is an essential but highly challenging component of artificial general intelligence. The absence of extensive annotated datasets has significantly impeded advancements in this field. We present EmotionCLIP, the first pre-training paradigm to extract visual emotion representations from verbal and nonverbal communication using only uncurated data. Compared to numerical labels or descriptions used in previous methods, communication naturally contains emotion information. Furthermore, acquiring emotion representations from communication is more congruent with the human learning process. We guide EmotionCLIP to attend to nonverbal emotion cues through subject-aware context encoding and verbal emotion cues using sentiment-guided contrastive learning. Extensive experiments validate the effectiveness and transferability of EmotionCLIP. Using merely linear-probe evaluation protocol, EmotionCLIP outperforms the state-of-the-art supervised visual emotion recognition methods and rivals many multimodal approaches across various benchmarks. We anticipate that the advent of EmotionCLIP will address the prevailing issue of data scarcity in emotion understanding, thereby fostering progress in related domains. The code and pre-trained models are available at https://github.com/Xeaver/EmotionCLIP.

Full Paper (including Appendix)
(high-resolution PDF, 3MB)

More information

Citation: Sitao Zhang, Yimu Pan and James Z. Wang, ``Learning Emotion Representations from Verbal and Nonverbal Communication,'' Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition, pp. 18993-19004, Vancouver, Canada, June 2023.

© 2023 IEEE/CVF. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE/CVF.

Last Modified: October 18, 2023
© 2023