Face aging and rejuvenation is applied to predict what a person looks like at different ages. While prior work brought about a significant progress in this topic, there are two central problems remaining to be solved : 1) most prior works require sequential data during training, while it is very rare in existing datasets; and 2) how to render an aging face and preserve personality at the same time. To deal with these problems, we develop a novel dual conditional GANs mechanism, thus aging faces can be trained with multiple sets of unlabeled facial images of different ages. Our basic architecture is AgeGAN, in which the primal conditional GAN converts input faces to other ages based on relevant age conditions, and the dual conditional GAN learns to invert the task. We further improve our networks, termed AgeGAN++, in which we share the weights between the primal part and the dual part to to streamline the model. Moreover, in order to get more sensible results, a representation disentanglement component is integrated with the latent facial representation, and an enhanced discriminator is applied on the generated process. In addition, we firstly perform an interpolation experiment to demonstrate that our generators are powerful and effective for face aging and rejuvenation. Experimental results on four public datasets demonstrate the appealing performance of the proposed methods by comparing with the state-of-the-art methods. Our code and a demo are released athttps://github.com/Sherry-JQ/AgeGAN.

In biology, evolution is the gradual change in the characteristics of a species over several generations. It has two properties: 1) The change is gradual, and 2) long-term changes are relied on short-term changes. Face aging/rejuvenation, which renders younger or elder facial images, follows the principles of evolution. Inspired by this, we propose an Evolutionary GANs (EvoGAN) for face aging/rejuvenation by making each age transformation smooth and decomposing a long-term transformation into several short-terms. Specifically, since short-term facial changes are gradual and relatively easy to render, we first divide the ages into several groups (i.e., chronologically from child, adult to elder). Then, for each pair of adjacent groups, we design two age transforms for face aging and rejuvenation, which are supposed to preserve personal identify information and predict age-specific characteristics. Compared with the mainstream for face aging/rejuvenation, i.e., conditional

Face aging and rejuvenation is to predict the face of a person at different ages. While tremendous progress have been made in this topic, there are two central problems remaining largely unsolved: 1) the majority of prior works requires sequential training data, which is very rare in real scenarios, and 2) how to simultaneously render aging face and preserve personality. To tackle these issues, in this paper, we develop a novel dual conditional GAN (DCGAN) mechanism, which enables face aging and rejuvenation to be trained from multiple sets of unlabeled face images with different ages. In our architecture, the primal conditional GAN transforms a face image to other ages based on the age condition, while the dual conditional GAN learns to invert the task. Hence a loss function that accounts for the reconstruction error of images can preserve the personal identity, while the discriminators on the generated images learn the transition patterns (e.g., the shape and texture changes between age groups) and guide the generation of age-specific photo-realistic faces. Experimental results on two publicly dataset demonstrate the appealing performance of the proposed framework by comparing with the state-of-the-art methods.

Reliable and fast message dissemination for safety application and quality-of-service (QoS) guarantee for data service are considered to be the most demanding requirements in vehicle ad-hoc networks. Current medium access control (MAC) protocols are insufficient to meet both requirements, while the standardization process is still ongoing. In this paper, an overlay token ring protocol (OTRP) is proposed for inter-vehicle communication (IVC). In the OTRP, the vehicular network is considered as overlapped virtual rings, each of which has a token passed in the ring as the right for transmission. The ring structure is dynamically adjusted according to the movements of vehicles. A salient feature of the OTRP is that two operation modes, namely the normal and emergency modes, are devised, whereby timely emergency message dissemination is guaranteed and desired quality-of-service (QoS) for data service can be provided. Theoretical analysis and simulations under saturated traffic condition are conducted. The results show that the OTRP can meet the stringent requirements of vehicle communications with fast and reliable emergency message broadcasting.

Localized mobility management is critical to achieve low handoff delay and signaling cost. However, the existing solutions may not be suitable for emerging wireless mesh networks (WMNs), which are characterized by the direct interconnectivity between access points. To exploit this feature of WMN, in this paper, we propose a novel localized mobility management scheme, called mobility-aware multi-path (MAMP) forwarding scheme, by utilizing multi-path routing. Our scheme can significantly improve the handoff processing performance at a slightly increased cost of control and management overhead. Extensive performance evaluations demonstrate that MAMP is superior to the existing solutions in terms of handoff delay, signaling amount as well as network scalability. Moreover, the proposed scheme can also achieve a better stability and reliability by adopting multi-path packet forwarding strategy.

Soft handoff and call admission control (CAC) in a packet switching CDMA wireless cellular system are studied. A normal cell area is divided into an inner cell area and a handoff area, based on which a cell capacity vector and a call admission region are derived for uplink transmission to satisfy user quality of service (QoS) requirements and to minimize the grade of service (GoS) function. The QoS parameters under consideration arc the transmission bit error rate (BER) and packet loss rate (PLR). The BER requirement is guaranteed by properly arranging simultaneous packet transmissions, whereas the PLR requirement is satisfied by proper packet scheduling for calls in the inner cell and handoff areas. The GoS function is minimized by considering both new call blocking and handoff call dropping probabilities. By taking traffic characteristics and dynamic scheduling of nonhandoff and handoff calls into account, the proposed packet scheduling scheme achieves fair packet transmissions and greatly enlarges the call admission region.