Fitting Different Interactive Information: Joint Classification of Emotion and Intention
This work addresses low-resource multimodal recognition for emotion and intention, but it is incremental as it builds on existing competition methods.
The paper tackles low-resource multimodal emotion and intention recognition by using pseudo-labeling on unlabeled data and leveraging intention recognition to mutually promote emotion recognition, achieving a score of 0.5532 on the test set and winning the competition.
This paper is the first-place solution for ICASSP MEIJU@2025 Track I, which focuses on low-resource multimodal emotion and intention recognition. How to effectively utilize a large amount of unlabeled data, while ensuring the mutual promotion of different difficulty levels tasks in the interaction stage, these two points become the key to the competition. In this paper, pseudo-label labeling is carried out on the model trained with labeled data, and samples with high confidence and their labels are selected to alleviate the problem of low resources. At the same time, the characteristic of easy represented ability of intention recognition found in the experiment is used to make mutually promote with emotion recognition under different attention heads, and higher performance of intention recognition is achieved through fusion. Finally, under the refined processing data, we achieve the score of 0.5532 in the Test set, and win the championship of the track.