[Objective] The research extensively utilizes the complementarity of modalities to enhance the correlation between different modalities and between modalities and labels, leading to highly accurate classification results. [Methods] The research introduces a novel algorithm for multi-label classification of short videos, which leverages multi-modal semantic enhancement and graph convolutional networks. The algorithm seamlessly integrates both multi-modal learning and label semantic learning within a unified network framework. [Results]This paper verifies the effectiveness of the proposed algorithm through a large number of experimental analyses, and the algorithm's classification accuracy reaches 87%, which is 6.82% higher than the optimal benchmark algorithm.[Limitations] The process of modality fusion to enhance information is hindered by the presence of redundant data, which in turn obscures the correlation between modalities. Furthermore, the domain of modality-based multi-label classification remains relatively unexplored with limited research available. [Conclusions] The algorithm effectively enhances the complementarity among modalities, strengthens the correlation between modalities and categories, and greatly improves the accuracy of classification.