Biphasic facial age translation aims at predicting the appearance of the input face at any age. Facial age translation has received considerable research attention in the last decade due to its practical value in cross-age face recognition and variou
s entertainment applications. However, most existing methods model age changes between holistic images, regardless of the human face structure and the age-changing patterns of individual facial components. Consequently, the lack of semantic supervision will cause infidelity of generated faces in detail. To this end, we propose a unified framework for biphasic facial age translation with noisy-semantic guided generative adversarial networks. Structurally, we project the class-aware noisy semantic layouts to soft latent maps for the following injection operation on the individual facial parts. In particular, we introduce two sub-networks, ProjectionNet and ConstraintNet. ProjectionNet introduces the low-level structural semantic information with noise map and produces soft latent maps. ConstraintNet disentangles the high-level spatial features to constrain the soft latent maps, which endows more age-related context into the soft latent maps. Specifically, attention mechanism is employed in ConstraintNet for feature disentanglement. Meanwhile, in order to mine the strongest mapping ability of the network, we embed two types of learning strategies in the training procedure, supervised self-driven generation and unsupervised condition-driven cycle-consistent generation. As a result, extensive experiments conducted on MORPH and CACD datasets demonstrate the prominent ability of our proposed method which achieves state-of-the-art performance.
Genomic surveillance of SARS-CoV-2 has been instrumental in tracking the spread and evolution of the virus during the pandemic. The availability of SARS-CoV-2 molecular sequences isolated from infected individuals, coupled with phylodynamic methods,
have provided insights into the origin of the virus, its evolutionary rate, the timing of introductions, the patterns of transmission, and the rise of novel variants that have spread through populations. Despite enormous global efforts of governments, laboratories, and researchers to collect and sequence molecular data, many challenges remain in analyzing and interpreting the data collected. Here, we describe the models and methods currently used to monitor the spread of SARS-CoV-2, discuss long-standing and new statistical challenges, and propose a method for tracking the rise of novel variants during the epidemic.
Binary star systems are assumed to be co-natal and coeval, thus to have identical chemical composition. In this work we aim to test the hypothesis that there is a connection between observed element abundance patterns and the formation of planets usi
ng binary stars. Moreover, we also want to test how atomic diffusion might influence the observed abundance patterns. We conduct a strictly line-by-line differential chemical abundance analysis of 7 binary systems. Stellar atmospheric parameters and elemental abundances are obtained with extremely high precision (< 3.5%) using the high quality spectra from VLT/UVES and Keck/HIRES. We find that 4 of 7 binary systems show subtle abundance differences (0.01 - 0.03 dex) without clear correlations with the condensation temperature, including two planet-hosting pairs. The other 3 binary systems exhibit similar degree of abundance differences correlating with the condensation temperature. We do not find any clear relation between the abundance differences and the occurrence of known planets in our systems. Instead, the overall abundance offsets observed in the binary systems (4 of 7) could be due to the effects of atomic diffusion. Although giant planet formation does not necessarily imprint chemical signatures onto the host star, the differences in the observed abundance trends with condensation temperature, on the other hand, are likely associated with diverse histories of planet formation (e.g., formation location). Furthermore, we find a weak correlation between abundance differences and binary separation, which may provide a new constraint on the formation of binary systems.
This paper investigates an aerial reconfigurable intelligent surface (RIS)-aided communication system under the probabilistic line-of-sight (LoS) channel, where an unmanned aerial vehicle (UAV) equipped with an RIS is deployed to assist two ground no
des in their information exchange. An optimization problem with the objective of maximizing the minimum average achievable rate is formulated to design the communication scheduling, the RISs phase, and the UAV trajectory. To solve such a non-convex problem, we propose an efficient iterative algorithm to obtain its suboptimal solution. Simulation results show that our proposed design significantly outperforms the existing schemes and provides new insights into the elevation angle and distance trade-off for the UAV-borne RIS communication system.
As the standardization of 5G is being solidified, researchers are speculating what 6G will be. Integrating sensing functionality is emerging as a key feature of the 6G Radio Access Network (RAN), allowing to exploit the dense cell infrastructure of 5
G for constructing a perceptive network. In this paper, we provide a comprehensive overview on the background, range of key applications and state-of-the-art approaches of Integrated Sensing and Communications (ISAC). We commence by discussing the interplay between sensing and communications (S&C) from a historical point of view, and then consider multiple facets of ISAC and its performance gains. By introducing both ongoing and potential use cases, we shed light on industrial progress and standardization activities related to ISAC. We analyze a number of performance tradeoffs between S&C, spanning from information theoretical limits, tradeoffs in physical layer performance, to the tradeoff in cross-layer designs. Next, we discuss signal processing aspects of ISAC, namely ISAC waveform design and receive signal processing. As a step further, we provide our vision on the deeper integration between S&C within the framework of perceptive networks, where the two functionalities are expected to mutually assist each other, i.e., communication-assisted sensing and sensing-assisted communications. Finally, we summarize the paper by identifying the potential integration between ISAC and other emerging communication technologies, and their positive impact on the future of wireless networks.
Image matting and image harmonization are two important tasks in image composition. Image matting, aiming to achieve foreground boundary details, and image harmonization, aiming to make the background compatible with the foreground, are both promisin
g yet challenging tasks. Previous works consider optimizing these two tasks separately, which may lead to a sub-optimal solution. We propose to optimize matting and harmonization simultaneously to get better performance on both the two tasks and achieve more natural results. We propose a new Generative Adversarial (GAN) framework which optimizing the matting network and the harmonization network based on a self-attention discriminator. The discriminator is required to distinguish the natural images from different types of fake synthesis images. Extensive experiments on our constructed dataset demonstrate the effectiveness of our proposed method. Our dataset and dataset generating pipeline can be found in url{https://git.io/HaMaGAN}
Semantic segmentation requires per-pixel prediction for a given image. Typically, the output resolution of a segmentation network is severely reduced due to the downsampling operations in the CNN backbone. Most previous methods employ upsampling deco
ders to recover the spatial resolution. Various decoders were designed in the literature. Here, we propose a novel decoder, termed dynamic neural representational decoder (NRD), which is simple yet significantly more efficient. As each location on the encoders output corresponds to a local patch of the semantic labels, in this work, we represent these local patches of labels with compact neural networks. This neural representation enables our decoder to leverage the smoothness prior in the semantic label space, and thus makes our decoder more efficient. Furthermore, these neural representations are dynamically generated and conditioned on the outputs of the encoder networks. The desired semantic labels can be efficiently decoded from the neural representations, resulting in high-resolution semantic segmentation predictions. We empirically show that our proposed decoder can outperform the decoder in DeeplabV3+ with only 30% computational complexity, and achieve competitive performance with the methods using dilated encoders with only 15% computation. Experiments on the Cityscapes, ADE20K, and PASCAL Context datasets demonstrate the effectiveness and efficiency of our proposed method.
In this paper, we propose an efficient algorithm for the network slicing problem which attempts to map multiple customized virtual network requests (also called services) to a common shared network infrastructure and allocate network resources to mee
t diverse service requirements. The problem has been formulated as a mixed integer linear programming (MILP) formulation in the literature. By exploiting the special structure of the network slicing problem, we first propose a novel linear programming (LP) relaxation of the MILP formulation. We show that compared with a natural LP relaxation of the MILP formulation, the novel LP relaxation is much more compact in terms of smaller numbers of variables and constraints, and much stronger in terms of providing a better LP bound, which makes it particularly suitable to be embedded in an LP based algorithm. Then we design an efficient two-stage LP rounding-and-refinement algorithm based on this novel LP relaxation. In the first stage, the proposed algorithm uses an iterative LP rounding procedure to place the virtual network functions of all services into cloud nodes while taking traffic routing of all services into consideration; in the second stage, the proposed algorithm uses an iterative LP refinement procedure to obtain a solution for traffic routing of all services with their end-to-end delay constraints being satisfied. Compared with the existing algorithms which either have an exponential complexity or return a low-quality solution, our proposed algorithm achieves a better trade-off between the solution quality and the computational complexity. In particular, the worst-case complexity of our proposed algorithm is polynomial, which makes it suitable for solving large-scale problems. Numerical results demonstrate the effectiveness and efficiency of our proposed algorithm.
In this demo, we present VirtualConductor, a system that can generate conducting video from any given music and a single users image. First, a large-scale conductor motion dataset is collected and constructed. Then, we propose Audio Motion Correspond
ence Network (AMCNet) and adversarial-perceptual learning to learn the cross-modal relationship and generate diverse, plausible, music-synchronized motion. Finally, we combine 3D animation rendering and a pose transfer model to synthesize conducting video from a single given users image. Therefore, any user can become a virtual conductor through the system.
Encouraging progress has been made towards Visual Question Answering (VQA) in recent years, but it is still challenging to enable VQA models to adaptively generalize to out-of-distribution (OOD) samples. Intuitively, recompositions of existing visual
concepts (i.e., attributes and objects) can generate unseen compositions in the training set, which will promote VQA models to generalize to OOD samples. In this paper, we formulate OOD generalization in VQA as a compositional generalization problem and propose a graph generative modeling-based training scheme (X-GGM) to handle the problem implicitly. X-GGM leverages graph generative modeling to iteratively generate a relation matrix and node representations for the predefined graph that utilizes attribute-object pairs as nodes. Furthermore, to alleviate the unstable training issue in graph generative modeling, we propose a gradient distribution consistency loss to constrain the data distribution with adversarial perturbations and the generated distribution. The baseline VQA model (LXMERT) trained with the X-GGM scheme achieves state-of-the-art OOD performance on two standard VQA OOD benchmarks, i.e., VQA-CP v2 and GQA-OOD. Extensive ablation studies demonstrate the effectiveness of X-GGM components.
