The production of traditional Peking opera facial masks often relies on hand painting by experienced painters, which restricts the inheritance and development of this intangible cultural heritage. Current research mainly focuses on the digital reconstruction and storage of existing Peking opera facial masks, while high-quality facial mask generation technology is still in an infancy stage. In this paper, different deep learning frameworks are improved for learning features of Peking opera facial masks and generating new masks, which can effectively promote the creative application of Peking opera facial masks. First, using different data enhancement methods, an improved Style Generative Adversarial Network-2 (StyleGAN2) can learn implicit and explicit features of Peking opera facial masks and automatically generate new facial masks. In addition, an image translation framework for joint cross-domain communication under weak supervision is used to translate face sketches and color reference maps to an intermediate feature domain, and then synthesize new facial masks through an image generation network. The experimental results show that the generated Peking opera facial masks have good local randomness and excellent visual quality.

Multimodal sentiment analysis (MSA) is important for quickly and accurately understanding people’s attitudes and opinions about an event. However, existing sentiment analysis methods suffer from the dominant contribution of text modality in the dataset; this is called text dominance. In this context, we emphasize that weakening the dominant role of text modality is important for MSA tasks. To solve the above two problems, from the perspective of datasets, we first propose the Chinese multimodal opinion-level sentiment intensity (CMOSI) dataset. Three different versions of the dataset were constructed: manually proofreading subtitles, generating subtitles using machine speech transcription, and generating subtitles using human cross-language translation. The latter two versions radically weaken the dominant role of the textual model. We randomly collected 144 real videos from the Bilibili video site and manually edited 2557 clips containing emotions from them. From the perspective of network modeling, we propose a multimodal semantic enhancement network (MSEN) based on a multiheaded attention mechanism by taking advantage of the multiple versions of the CMOSI dataset. Experiments with our proposed CMOSI show that the network performs best with the text-unweakened version of the dataset. The loss of performance is minimal on both versions of the text-weakened dataset, indicating that our network can fully exploit the latent semantics in nontext patterns. In addition, we conducted model generalization experiments with MSEN on MOSI, MOSEI, and CH-SIMS datasets, and the results show that our approach is also very competitive and has good cross-language robustness.

Existing outdoor three-dimensional (3D) object detection algorithms mainly use a single type of sensor, for example, only using a monocular camera or radar point cloud. However, camera sensors are affected by light and lose depth information. When scanning a distant object or an occluded object, the data collected by the short-range radar point cloud sensor are very sparse, which affects the detection algorithm. To address the above challenges, we design a deep learning network that can combine the texture information of two-dimensional (2D) data and the geometric information of 3D data for object detection. To solve the problem of a single sensor, we use a reverse mapping layer and an aggregation layer to combine the texture information of RGB data with the geometric information of point cloud data and design a maximum pooling layer to deal with the input of multi-view cameras. In addition, to solve the defects of the 3D object detection algorithm based on the region proposal network (RPN) method, we use the Hough voting algorithm implemented by a deep neural network to suggest objects. Experimental results show that our algorithm has a 1.06% decrease in average precision (AP) compared to PointRCNN in easy car object detection, but our algorithm requires 37.7% less time to calculate than PointRCNN under the same hardware environment. Moreover, our algorithm improves the AP by 1.14% compared to PointRCNN in hard car object detection.

A modified total variation MRI image denoising method is proposed in this paper. First, the proposed method removes the noise in K-space in compressed sensing MRI reconstruction. Then, the removed K-space data is used as a partial frequency observation in compressed sensing MRI model. The proposed method shows better results than RecPF method, LDP method, TVCMRI method, and FCSA method in sparse MRI reconstruction. The proposed method is tested against Shepp-Logan phantom and real MR images corrupted by noise of different intensity level, and it gives better Signal-to-Noise Ratio (SNR), the relative error (ReErr), and the structural similarity (SSIM) than RecPF, LDP, TVCMRI, and FCSA.

Instruction tuning large language models are making rapid advances in the field of artificial intelligence where GPT-4 models have exhibited impressive multi-modal perception capabilities. Such models have been used as the core assistant for many tasks including art generation. However, high-quality art generation relies heavily on human prompt engineering which is in general uncontrollable. To address these issues, we propose a multi-task AI generated content (AIGC) system for art generation. Specifically, a dense representation manager is designed to process multi-modal user queries and generate dense and applicable prompts to GPT. To enhance artistic sophistication of the whole system, we fine-tune the GPT model by a meticulously collected prompt-art dataset. Furthermore, we introduce artistic benchmarks for evaluating the system based on professional knowledge. Experiments demonstrate the advantages of our proposed MtArtGPT system.