Learning Emotion Representations from Verbal and Nonverbal Communication

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 Emotion-CLIP, 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 validates the effectiveness and transferability of EmotionCLIP. Using merely linear-probe evaluation protocol, EmotionCLIP outperforms the state-of-theart 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 . * equal contribution Conversation: -Dad. Who is Dede? -Jesus. She was the love of my life and I was too stupid to realized it. I lost her because of something so dumb. 0 1 1 0 0 Categorical Label: Shocked Regretful Description: An old man is chatting with his son while eating at a restaurant.