Remote photoplethysmography (rPPG) achieves non-contact heart rate monitoring by detecting subtle skin color variations in facial videos, offering significant potential in healthcare, fitness, and security applications.However, accurately extracting rPPG signals in complex environments-especially under variable lighting and motion artifacts-remains challenging. The main difficulties are capturing spatio-temporal dynamics and modeling long-term dependencies across channels. To address these limitations, we propose MaKAN-Mixer, a novel end-to-end network designed to enhance the robustness and accuracy of rPPG signal extraction. First, MaKAN-Mixer integrates a Hybrid of Eulerian Video Magnification and Temporal Shift Module Amplification (HETA) to amplify subtle physiological signals and enhance temporal information without relying on explicit region-of-interest (ROI) selection. Additionally, we propose the Mamba-KAN Fusion Module (MKFM), which leverages Mamba's ability to efficiently model long-term dependencies in temporal sequences. By incorporating the Kolmogorov-Arnold Network (KAN) for effective channel mixing, MKFM ensures the comprehensive fusion of relevant spatio-temporal features across different channels. Finally, we employ a KAN Feedforward Neural Network (KFN) to capture complex, nonlinear, and periodic physiological patterns, improving heart rate estimation. Extensive experiments conducted on four benchmark datasets demonstrate that MaKAN-Mixer achieves superior performance in both intra- and cross-dataset testing, exhibiting exceptional robustness in challenging scenarios, particularly with compressed video data and complex environments. In comparison to the best-performing existing method, which reported RMSE values of 0.78/0.47/4.57/6.81 on the four datasets, MaKAN-Mixer significantly improves the RMSE to 0.66/0.40/0.32/6.25, highlighting its effectiveness across diverse conditions. Furthermore, novel visualization techniques were employed for qualitative validation of the results, underscoring its potential for accurate, real-world rPPG monitoring.

In this paper, Reconfigurable Intelligent Surface (RIS) is introduced into 2D radar to achieve target height estimation. Taking advantage of the wide beam of the 2D radar in the pitch dimension, several RISs, which may be carried by the UAVs, are set up in the receiving beam in the pitch dimension to construct multiple auxiliary measurement channels. The auxiliary channel measurements are used to realize the target height estimation combined with the target measurements in 2D radar by solving a least square problem with convex optimization method. The proposed RIS-assisted target height estimation method is verified by the simulation results, and the influence of the number and the locations of the RISs on the estimation accuracy is covered.

The massive amount of data on the Internet of Things (IoT) drives recommendation systems (RSs) based on graph neural network (GNN) to fully play a role in improving user experience. However, data sharing and centralized storage can pose serious security threats. Even though federated learning (FL) can render data “available but not visible,” the heterogeneity of graph data within IoT institutions can result in limitations in recommendation performance. To address the issues, we propose a privacy-preserving decentralized cross-institutional federated graph learning framework called DCI-PFGL for IoT service recommendation, which alleviates the negative impact of data heterogeneity while protecting data security. Our approach extracts graph feature embeddings using the shortest path graph kernel. These embeddings are then anonymized and compared on a blockchain through smart contracts, which helps match partner IoT institutions with lower data heterogeneity. Subsequently, IoT institutions within the same partition collaborate in federated graph learning. We also ensure the protection of transmitted information through differential privacy measures. Finally, we conduct comprehensive experiments on two benchmark data sets. Results demonstrate that DCI-PFGL outperforms other approaches in terms of system accuracy and collaboration costs.

We propose a novel approach for generating paths with desired exertion properties, which can be used for delivering highly realistic and immersive virtual reality applications that help users achieve exertion goals. Given a terrain as input, our optimization-based approach automatically generates feasible paths on the terrain which users can bike to perform body training in virtual reality. The approach considers exertion properties such as the total work and the perceived level of path difficulty in generating the paths. To verify our approach, we applied it to generate paths on a variety of terrains with different exertion targets and constraints. To conduct our user studies, we built an exercise bike whose force feedback was controlled by the elevation angle of the generated path over the terrain. Our user study results showed that users found exercising with our generated paths in virtual reality more enjoyable compared to traditional exercising approaches. Their energy expenditure in biking the generated paths also matched with the specified targets, validating the efficacy of our approach.

Player's physical experience is a critical factor to consider in designing motion-based games that are played through motion sensor gaming consoles or virtual reality devices. However, adjusting the physical challenge involved in a motion-based game is difficult and tedious, as it is typically done manually by level designers on a trial-and-error basis. In this paper, we propose a novel approach for automatically synthesizing levels for motion-based games that can achieve desired physical movement goals. By formulating the level design problem as a trans-dimensional optimization problem which is solved by a reversible-jump Markov chain Monte Carlo technique, we show that our approach can automatically synthesize a variety of game levels, each carrying the desired physical movement properties. To demonstrate the generality of our approach, we synthesize game levels for two different types of motion-based games and conduct a user study to validate the effectiveness of our approach.

The Amazon Picking Challenge and the Amazon Robotics Challenge have shown significant progress in object picking from a cluttered scene, yet object placement remains challenging. It is useful to have pose-aware placement based on human and machine readable pieces on an object. For example, the brandname of an object placed on a shelf should be facing the human customers. The robotic vision challenges in the object placement task: a) the semantics and geometry of the object to be placed need to be analysed jointly; b) and the occlusions among objects in a cluttered scene could make it hard for proper understanding and manipulation. To overcome these challenges, we develop a pose-aware placement approach by spotting the semantic labels (e.g., brandnames) of objects in a cluttered tote and then carrying out a sequence of actions to place the objects on a shelf or on a conveyor with desired poses. Our major contributions include 1) providing an open benchmark dataset of objects and brandnames with multi-view segmentation for training and evaluations; 2) carrying out comprehensive evaluations for our brandname-based fully convolutional network (FCN) that can predict the affordance and grasp to achieve pose-aware placement, whose success rates decrease along with clutters; 3) showing that active manipulation with two cooperative manipulators and grippers can effectively handle the occlusion of brandnames. We analyzed the success rates and discussed the failure cases to provide insights for future applications. All data and benchmarks are available at https://text-pick-n-place.github.io/TextPNP/.

Games and experiences designed for virtual or augmented reality usually require the player to move physically to play. This poses substantial challenge for level designers because the player's physical experience in a level will need to be considered, otherwise the level may turn out to be too exhausting or not challenging enough. This paper presents a novel approach to optimize level designs by considering the physical challenge imposed upon the player in completing a level of motion-based games. A game level is represented as an assembly of chunks characterized by the exercise intensity levels they impose on players. We formulate game level synthesis as an optimization problem, where the chunks are assembled in a way to achieve an optimized level of intensity. To allow the synthesis of game levels of varying lengths, we solve the trans-dimensional optimization problem with a Reversible-jump Markov chain Monte Carlo technique. We demonstrate that our approach can be applied to generate game levels for s of motion-based virtual reality games. A user evaluation validates the effectiveness of our approach in generating levels with the desired amount of physical challenge.