Motion capture technology is one of the key topics of current research, with researchers exploring its applications in fields such as sports, entertainment, and video games. However, there is a research gap in current mainstream motion capture analysis based on different sensors. This study analyzes motion capture systems using contact and non-contact sensors, discussing their respective advantages, disadvantages, and solutions, particularly in terms of their performance in various industries, as well as issues such as data drift, accuracy, and cost. The research methods involve multiple capturing techniques included in both contact and non-contact motion capture. The results indicate that future motion capture technology will focus on cost optimization, device miniaturization, and markerless technology development. Additionally, motion capture has potential applications in psychology, with a hypothesis proposed for the development of emotion-responsive motion capture through in-depth integration with AI, which could be a major breakthrough. This evolution of motion capture technology aims to foster innovation across more application fields.

Show more

Ever since 2022, there has been a large number of 3D generative models that have been devised and published, such as AvatarGen, CityDreamer, and HOLOFUSION. Generally speaking, these models can perform tasks such as generating a 3D human model, creating an unbounded city scene, and constructing a 3D object. And it is not a surprise that 3D generative models are very popular these years because there has been a witness of huge need for 3D models in the global market and the models themselves also serve as both convenient and productive tools for the relevant industries. For instance, 3D generative models can utilize a combination of Generative Adversarial Network (GAN) and Multi-Layer Perceptron (MLP) or Neural Radiance Field (NeRF) or Diffusion Model to produce 3D human model; Autoregressive Model or Feature Extraction + Volume Rendering to generate 3D scenes; Diffusion Model or GAN + MLP to produce 3D objects. This paper tries to present a taxonomy of the main 3D generative models from the angle of the kinds of outputs and strategies employed by different models.

Show more

Multimodal sentiment analysis is one of the important research areas in the field of artificial intelligence today. Multimodal sentiment analysis is to extract features from various human modalities such as facial expressions, body movements, and voice information, perform modal fusion, and finally classify and predict emotions. This technology can be used in multiple scenarios such as stock prediction, product analysis, movie box office prediction, etc., especially psychological state analysis, and has important research significance. This paper introduces two important datasets in multimodal sentiment analysis, namely CMU-MOSEI and IEMOCAP. It also introduces the feature-level fusion, model-level fusion, decision-level fusion and other fusion methods in multimodal fusion methods, and also introduces the semantic feature fusion neural network and sentiment word perception fusion network in multimodal sentiment analysis related models. Finally, the application of multimodal sentiment analysis models in depression and other related mental illnesses and the challenges of multimodal sentiment analysis models in the future are introduced. This paper hopes that the above research will be helpful for multimodal sentiment analysis.

Show more

This paper combines the current research status of wireless networks and artificial intelligence, delving into the state of wireless network research and its impacts, and highlights the importance and necessity of the integrated development of wireless networks and AI. The aim is to provide readers with an understanding of the current situation and challenges of wireless networks. With the increasing number of mobile communication users, spectrum resources are becoming increasingly scarce, network security issues are more prominent, and the complexity of network architecture and business processes has significantly increased, making it difficult for traditional operations and maintenance methods to meet these demands. Therefore, leveraging AI to build a new mode of communication network operation has become an inevitable choice. The intelligent evolution of wireless networks is an unstoppable trend. In the future, full intelligence will be achieved through digital infrastructure, knowledge introduction, and digital twins, driving the efficient development of wireless networks.

Show more