Related papers: Cross-artform performance using networked interfac…
Non-contact physiological measurement has the potential to provide low-cost, non-invasive health monitoring. However, machine vision approaches are often limited by the availability and diversity of annotated video datasets resulting in…
Reconstructing physically plausible 3D human-scene interactions (HSI) from a single image currently presents a trade-off: optimization based methods offer accurate contact but are slow (~20s), while feed-forward approaches are fast yet lack…
Our team of dance artists, physicists, and machine learning researchers has collectively developed several original, configurable machine-learning tools to generate novel sequences of choreography as well as tunable variations on input…
This paper presents a novel multimodal human activity recognition system. It uses a two-stream decision level fusion of vision and inertial sensors. In the first stream, raw RGB frames are passed to a part affinity field-based pose…
The application of mobile biometrics as a user-friendly authentication method has increased in the last years. Recent studies have proposed novel behavioral biometric recognition systems based on Transformers, which currently outperform the…
During the last two years the RealityGrid project has allowed us to be one of the few scientific groups involved in the development of computational grids. Since smoothly working production grids are not yet available, we have been able to…
Live interactions have the potential to meaningfully engage audiences during musical performances, and modern technologies promise unique ways to facilitate these interactions. This work presents findings from three co-design sessions with…
Human action recognition (HAR) is a high-level and significant research area in computer vision due to its ubiquitous applications. The main limitations of the current HAR models are their complex structures and lengthy training time. In…
Interacting systems are increasingly common. Many examples pervade our everyday lives: automobiles, aircraft, defense systems, telephone switching systems, financial systems, national governments, and so on. Closer to computer science,…
This paper introduces Stringesthesia, an interactive and improvised performance paradigm. Stringesthesia uses real-time neuroimaging to connect performers and audiences, enabling direct access to the performers mental state and determining…
With the growing demand for live video streaming, there is an increasing need for low-latency and high-quality transmission, especially with the advent of 5G networks. While 5G offers hardware-level improvements, effective software…
Integrating technology with the distinctive characteristics of craftsmanship has become a key issue in the field of digital craftsmanship. This paper introduces Layered Interactions, a design approach that seamlessly merges Human-Computer…
Coordination is one of the most difficult aspects of multi-agent reinforcement learning (MARL). One reason is that agents normally choose their actions independently of one another. In order to see coordination strategies emerging from the…
We present LARNet, a novel end-to-end approach for generating human action videos. A joint generative modeling of appearance and dynamics to synthesize a video is very challenging and therefore recent works in video synthesis have proposed…
Robotic avatar systems promise to bridge distances and reduce the need for travel. We present the updated NimbRo avatar system, winner of the $5M grand prize at the international ANA Avatar XPRIZE competition, which required participants to…
We propose a novel neural rendering pipeline, Hybrid Volumetric-Textural Rendering (HVTR), which synthesizes virtual human avatars from arbitrary poses efficiently and at high quality. First, we learn to encode articulated human motions on…
Accurately and efficiently simulating complex fluid dynamics is a challenging task that has traditionally relied on computationally intensive methods. Neural network-based approaches, such as convolutional and graph neural networks, have…
For human pose estimation in videos, it is significant how to use temporal information between frames. In this paper, we propose temporal flow maps for limbs (TML) and a multi-stride method to estimate and track human poses. The proposed…
This paper proposed a hierarchical visible autoencoder in the adaptive phantom limbs generation according to the kinetic behavior of functional body-parts, which are measured by heterogeneous kinetic sensors. The proposed visible…
Manually authoring transition animations for a complete locomotion system can be a tedious and time-consuming task, especially for large games that allow complex and constrained locomotion movements, where the number of transitions grows…