The invention discloses a multi-mode collaborative learning method and apparatus based on a neural network. The method comprises the following steps: S1 capturing short video data to establish a shortvideo data set, wherein the short video data comprise short videos published by a user historically and subsidiary information thereof; S2 extracting multi-mode features of the short video data in the short video data set, and performing information complement for the multi-mode features; S3 sequentially taking any modal feature in the modal features as a main mode and using the modal features asauxiliary modes, calculating the relationship weights of the main mode and the auxiliary modes, respectively classifying identical feature information and supplementary feature information, and performing information recombination on the supplementary feature information and the identical feature information enhanced by the neural network; and S4 establishing an attention mechanism network, distinguishing the degree of contribution of each piece of recombined mode feature information a scene category to which the short videos belong, and performing short video scene classification by using the neural network.