Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis

2 code implementations • 9 Feb 2021 • Wenmeng Yu, Hua Xu, Ziqi Yuan, Jiele Wu

On MOSI and MOSEI datasets, our method surpasses the current state-of-the-art methods.

Multimodal Sentiment Analysis Multi-Task Learning +2

Toward Effective Automated Content Analysis via Crowdsourcing

no code implementations • 12 Jan 2021 • Jiele Wu, Chau-Wai Wong, Xinyan Zhao, Xianpeng Liu

For subjective features such as semantic connotation, online workers, known for optimizing their hourly earnings, tend to deteriorate in the quality of their responses as they work longer.

CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotation of Modality

1 code implementation • ACL 2020 • Wenmeng Yu, Hua Xu, Fanyang Meng, Yilin Zhu, Yixiao Ma, Jiele Wu, Jiyun Zou, Kai-Cheng Yang

Previous studies in multimodal sentiment analysis have used limited datasets, which only contain unified multimodal annotations.

Multimodal Sentiment Analysis Multi-Task Learning