The power consumption flexibility provided by the energy-intensive Internet data centers (IDCs) has been extensively studied as a potential solution for enhancing the flexibility of power systems. In IDCs, computational workloads are further divided into potentially interdependent tasks. To assess the power consumption flexibility of IDCs, it is necessary to consider the interdependency of computational tasks. However, there are no methods for deriving a task dependency-aware IDC load model that is easy to embed in the operation of power systems to fully utilize the power consumption flexibility of IDCs. To this end, this paper proposes a framework to derive a compatible task dependency-aware IDC load model. A linear IDC load model is formulated based on typical batch workloads given by a task dependency-aware clustering framework. Afterward, the Cost-Oriented Progressive Vertex Enumeration (COPVE) algorithm is proposed to derive an easy-to-embed IDC load model from the original linear model. Experiments show that the derived IDC load model accurately reflects the feasible region of the original IDC load model with fewer constraints compared with the model derived by the advanced Progressive Vertex Enumeration (PVE) algorithm.

The remote photoplethysmography (rPPG) technique can estimate pulse-related metrics (e.g. heart rate and respiratory rate) from facial videos and has a high potential for health monitoring. The latest deep rPPG methods can model in-distribution noise due to head motion, video compression, etc., and estimate high-quality rPPG signals under similar scenarios. However, deep rPPG models may not generalize well to the target test domain with unseen noise and distortions. In this paper, to improve the generalization ability of rPPG models, we propose a dual-bridging network to reduce the domain discrepancy by aligning intermediate domains and synthesizing the target noise in the source domain for better noise reduction. To comprehensively explore the target domain noise, we propose a novel adversarial noise generation in which the noise generator indirectly competes with the noise reducer. To further improve the robustness of the noise reducer, we propose hard noise pattern mining to encourage the generator to learn hard noise patterns contained in the target domain features. We evaluated the proposed method on three public datasets with different types of interferences. Under different crossdomain scenarios, the comprehensive results show the effectiveness of our method.

Test-time training (TTT) is an emerging approach for addressing the problem of domain shift. In its framework, a test-time training phase is inserted between the training phase and the test phase. During the test-time training phase, the representation layers are adapted using an auxiliary task. Then the updated model will be used in the test phase. Although the idea is very intuitive, TTT does not demonstrate competitive performance compared with some other domain adaption methods. In this paper, we present both theoretical and empirical analyses to explain the subpar performance of TTT. In particular, we point out that TTT causes a new kind of problem, which we term as Model Mismatch. To address this problem of Model Mismatch, we analyse a simple yet effective method inspired by the idea of mixup in robust training. Such effectiveness is shown in the experimental results.

Face presentation attack detection (fPAD) plays a critical role in the modern face recognition pipeline. The generalization ability of face presentation attack detection models to unseen attacks has become a key issue for real-world deployment, which can be improved when models are trained with face images from different input distributions and different types of spoof attacks. In reality, due to legal and privacy issues, training data (both real face images and spoof images) are not allowed to be directly shared between different data sources. In this paper, to circumvent this challenge, we propose a Federated Test-Time Adaptive Face Presentation Attack Detection with Dual-Phase Privacy Preservation framework, with the aim of enhancing the generalization ability of fPAD models in both training and testing phase while preserving data privacy. In the training phase, the proposed framework exploits the federated learning technique, which simultaneously takes advantage of rich fPAD information available at different data sources by aggregating model updates from them without accessing their private data. To further boost the generalization ability, in the testing phase, we explore test-time adaptation by minimizing the entropy of fPAD model prediction on the testing data, which alleviates the domain gap between training and testing data and thus reduces the generalization error of a fPAD model. We introduce the experimental setting to evaluate the proposed framework and carry out extensive experiments to provide various insights about the proposed method for fPAD.

Intra-frame distortion drift is a big problem of data hiding in H.264/AVC video streams. Based on a thorough investigation of this problem, a novel readable data-hiding algorithm, which can embed data into the quantized discrete cosine transform (DCT) coefficients of I frames without bringing any intra-frame distortion drift into the H.264/advanced video coding (AVC) video host, is presented in this paper. We exploit several paired-coefficients of a 4$\,\times\,$4 DCT block to accumulate the embedding induced distortion. The directions of intra-frame prediction are utilized to avert the distortion drift. It is proved analytically and shown experimentally that the proposed algorithm can achieve high embedding capacity and low visual distortion. Performance comparisons with other existing schemes are provided to demonstrate the superiority of the proposed scheme.