Multimodal movie genre classification has always been regarded as a demanding multi-label classification task due to the diversity of multimodal data such as posters, plot summaries, trailers and metadata. Although existing works have made great progress in modeling and combining each modality, they still face three issues: 1) unutilized group relations in metadata, 2) unreliable attention allocation, and 3) indiscriminative fused features. Given that the knowledge graph has been proven to contain rich information, we present a novel framework that exploits the knowledge graph from various perspectives to address the above problems. As a preparation, the metadata is processed into a domain knowledge graph. A translate model for knowledge graph embedding is adopted to capture the relations between entities. Firstly we retrieve the relevant embedding from the knowledge graph by utilizing group relations in metadata and then integrate it with other modalities. Next, we introduce an Attention Teacher module for reliable attention allocation based on self-supervised learning. It learns the distribution of the knowledge graph and produces rational attention weights. Finally, a Genre-Centroid Anchored Contrastive Learning module is proposed to strengthen the discriminative ability of fused features. The embedding space of anchors is initialized from the genre entities in the knowledge graph. To verify the effectiveness of our framework, we collect a larger and more challenging dataset named MM-IMDb 2.0 compared with the MM-IMDb dataset. The experimental results on two datasets demonstrate that our model is superior to the state-of-the-art methods. Our code and dataset is available at https://github.com/aoluming/IDKG.git.

Power management of application programs is a hot research in the area of green computing and high-productivity computing. Because of the complexity of application programs, heterogeneity of processors and uncertainty of the running environment, it is difficult to propose an accurate method to predict energy consumption for application program directly. So, we present a power analysis paradigm for application program based on artificial neural network. First, we build a power analysis model based on back propagation neural network (BPNN). The three factors of software, hardware and environment are taken as the inputs of BPNN, and energy consumption and finish time as the outputs of BPNN. Next, we choose lot of classic application programs from different fields as training samples. After learning and training, an expected BPNN is obtained which can be used to predict energy consumption for other new programs. Repeated experiments show that this power analysis paradigm is rational and feasible.