The task of text-to-image synthesis is to generate photographic images conditioned on given textual descriptions. This challenging task has recently attracted considerable attention from the multimedia community due to its potential applications. Most of the up-to-date approaches are built based on generative adversarial network (GAN) models, and they synthesize images conditioned on the global linguistic representation. However, the sparsity of the global representation results in training difficulties on GANs and a shortage of fine-grained information in the generated images. To address this problem, we propose cross-modal global and local linguistic representations-based generative adversarial networks (CGL-GAN) by incorporating the local linguistic representation into the GAN. In our CGL-GAN, we construct a generator to synthesize the target images and a discriminator to judge whether the generated images conform with the text description. In the discriminator, we construct the cross-modal correlation by projecting the image representations at high and low levels onto the global and local linguistic representations, respectively. We design the hinge loss function to train our CGL-GAN model. We evaluate the proposed CGL-GAN on two publicly available datasets, the CUB and the MS-COCO. The extensive experiments demonstrate that incorporating fine-grained local linguistic information with cross-modal correlation can greatly improve the performance of text-to-image synthesis, even when generating high-resolution images.
The key challenge of cross-modal domain-incremental learning (DIL) is to enable the learning model to continuously learn from novel data with different feature distributions under the same task without forgetting old ones. However, existing top-performing methods still cause high forgetting rates, by lacking intra-domain knowledge extraction and inter-domain common prompting strategy. In this paper, we propose a simple yet effective framework, CP-Prompt, by training limited parameters to instruct a pre-trained model to learn new domains and avoid forgetting existing feature distributions. CP-Prompt captures intra-domain knowledge by compositionally inserting personalized prompts into multi-head self-attention layers and then learns the inter-domain knowledge with a common prompting strategy. CP-Prompt shows superiority compared with state-of-the-art baselines among three widely evaluated DIL tasks. The source code is available at https://github.com/dannis97500/CP_Prompt.
Data prediction is proposed in wireless sensor networks (WSNs) to extend system lifetime by avoiding transmissions of redundant messages. Existing prediction-based approaches can be classified into two types. One focuses on historical data reconstruction and proposes backward models, which incur uncontrollable delay. The other focuses on the future data prediction and proposes forward models, which require additional transmissions. This letter proposes a hybrid model with the capabilities of both historical data reconstruction and future data prediction to avoid additional transmission and control delay. Two algorithms are proposed to implement this model in real-world WSNs. One is a stagewise algorithm for sensor nodes to build optimal models. The other is for the sink to reconstruct and predict sensed values. Two WSN applications are simulated based on three real data sets to evaluate the performances of the hybrid model. Simulation results demonstrate that the proposed approach has high performance in terms of energy efficiency with controllable delay.
This paper proposes an AI-based decision support system for enhancing energy efficiency in autonomous systems within consumer electronics. The primary objective is to optimize energy consumption by leveraging advanced Recurrent Neural Networks (RNNs) combined with Adaptive Moment Estimation (Adam). The proposed intelligent framework incorporates real-time data processing, prediction, and adaptive decision-making to reduce energy usage across a variety of devices, such as smart thermostats, robotic vacuum cleaners, and IoT-enabled lighting systems. Key methodologies include the integration of RNNs to model temporal energy consumption patterns and the Adam optimizer for efficient model training. The results demonstrate significant energy savings with improvements in prediction accuracy compared to traditional approaches. The findings suggest that the AI-based system can provide substantial reductions in energy consumption while maintaining or improving device performance. The research has important implications for the future of energy-efficient consumer electronics, particularly as the demand for smart devices grows.