Search

Humans naturally interact with both others and the surrounding multiple objects, engaging in various social activities. However, recent advances in modeling human-object interactions mostly focus on perceiving isolated individuals and objects, due to fundamental data scarcity. In this paper, we introduce HOI-M3, a novel large-scale dataset for modeling the interactions of Multiple huMans and Multiple objects. Notably, it provides accurate 3D tracking for both humans and objects from dense RGB and object-mounted IMU inputs, covering 199 sequences and 181M frames of diverse humans and objects under rich activities. With the unique HOI-M3 dataset, we introduce two novel data-driven tasks with companion strong baselines: monocular capture and unstructured generation of multiple human-object interactions. Extensive experiments demonstrate that our dataset is challenging and worthy of further research about multiple human-object interactions and behavior analysis. Our HOI-M3 dataset, corresponding codes, and pre-trained models will be disseminated to the community for future research., Comment: Accepted to CVPR 2024

We present Capturing the Unseen (CAPUS), a novel facial motion capture (MoCap) technique that operates without visual signals. CAPUS leverages miniaturized Inertial Measurement Units (IMUs) as a new sensing modality for facial motion capture. While IMUs have become essential in full-body MoCap for their portability and independence from environmental conditions, their application in facial MoCap remains underexplored. We address this by customizing micro-IMUs, small enough to be placed on the face, and strategically positioning them in alignment with key facial muscles to capture expression dynamics. CAPUS introduces the first facial IMU dataset, encompassing both IMU and visual signals from participants engaged in diverse activities such as multilingual speech, facial expressions, and emotionally intoned auditions. We train a Transformer Diffusion-based neural network to infer Blendshape parameters directly from IMU data. Our experimental results demonstrate that CAPUS reliably captures facial motion in conditions where visual-based methods struggle, including facial occlusions, rapid movements, and low-light environments. Additionally, by eliminating the need for visual inputs, CAPUS offers enhanced privacy protection, making it a robust solution for vision-free facial MoCap., Comment: Go to CAPUS project page https://sites.google.com/view/projectpage-capus and watch our video https://youtu.be/sR0GXxmBt8Y

In this paper, we develop and analyze a rigorous multiscale upscaling method for dual continuum model, which serves as a powerful tool in subsurface formation applications. Our proposed method is capable of identifying different continua and capturing non-local transfer and effective properties in the computational domain via constructing localized multiscale basis functions. The construction of the basis functions consists of solving local problems defined on oversampling computational region, subject to the energy minimizing constraints that the mean values of the local solution are zero in all continua except for the one targeted. The basis functions constructed are shown to have good approximation properties. It is shown that the method has a coarse mesh dependent convergence. We present some numerical examples to illustrate the performance of the proposed method.