التفاصيل البيبلوغرافية
| العنوان: |
Learning Emotion Representations from Verbal and Nonverbal Communication |
| المؤلفون: |
Zhang, Sitao, Pan, Yimu, Wang, James Z. |
| سنة النشر: |
2023 |
| المجموعة: |
ArXiv.org (Cornell University Library) |
| مصطلحات موضوعية: |
Computer Science - Computer Vision and Pattern Recognition |
| الوصف: |
Emotion understanding is an essential but highly challenging component of artificial general intelligence. The absence of extensively 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/EmotionCLIPTest. ; Comment: CVPR 2023 |
| نوع الوثيقة: |
text |
| اللغة: |
unknown |
| العلاقة: |
http://arxiv.org/abs/2305.13500Test |
| الإتاحة: |
http://arxiv.org/abs/2305.13500Test |
| رقم الانضمام: |
edsbas.95EF5A2D |
| قاعدة البيانات: |
BASE |
