Recent style translation methods have extended their transferability from texture to geometry. However, performing translation while preserving image content when there is a significant style difference is still an open problem. To overcome this problem, we propose Invertible Conditional Fast GAN (IcFGAN) based on GAN inversion and cFGAN. It allows for unpaired photo-to-manga face translation. Experimental results show that our method could translate styles under significant style gaps, while the state-of-the-art methods could hardly preserve image content.

Generating high-quality images with Generative Adversarial Networks (GANs) generally requires 100k+ training data. The required data amount is too large when we consider using GANs to support professional art creators; they need to follow the specific art style while interactively controlling the results along with their theme. This research proposes Conditional FastGAN, which adds a condition vector to FastGAN to produce high-quality different domain images even on small datasets. In our experiments, the MUCT Face Database of images consisting of face photos in various orientations and manga face images extracted from Osamu Tezuka’s works were used as a small-scale dataset. Fine-tuning with manga face images to a model pre-trained with photo-only face images enabled control of the generated images according to explicit conditions, such as photos and manga, for the same latent variables. In addition, the proposed method improved the FID score by 2.55 from the original FastGAN in the case of manga face generation.

Group cohesiveness reflects the level of intimacy that people feel with each other, and the development of a dialogue robot that can understand group cohesiveness will lead to the promotion of human communication. However, group cohesiveness is a complex concept that is difficult to predict based only on image pixels. Inspired by the fact that humans intuitively associate linguistic knowledge accumulated in the brain with the visual images they see, we propose a linguistic knowledge injectable deep neural network (LDNN) that builds a visual model (visual LDNN) for predicting group cohesiveness that can automatically associate the linguistic knowledge hidden behind images. LDNN consists of a visual encoder and a language encoder, and applies domain adaptation and linguistic knowledge transition mechanisms to transform linguistic knowledge from a language model to the visual LDNN. We train LDNN by adding descriptions to the training and validation sets of the Group AFfect Dataset 3.0 (GAF 3.0), and test the visual LDNN without any description. Comparing visual LDNN with various fine-tuned DNN models and three state-of-the-art models in the test set, the results demonstrate that the visual LDNN not only improves the performance of the fine-tuned DNN model leading to an MSE very similar to the state-of-the-art model, but is also a practical and efficient method that requires relatively little preprocessing. Furthermore, ablation studies confirm that LDNN is an effective method to inject linguistic knowledge into visual models.

Audio-video group emotion recognition is a challenging task since it is difficult to gather a broad range of potential information to obtain meaningful emotional representations. Humans can easily understand emotions because they can associate implicit contextual knowledge (contained in our memory) when processing explicit information they can see and hear directly. This paper proposes an end-to-end architecture called implicit knowledge injectable cross attention audiovisual deep neural network (K-injection audiovisual network) that imitates this intuition. The K-injection audiovisual network is used to train an audiovisual model that can not only obtain audiovisual representations of group emotions through an explicit feature-based cross attention audiovisual subnetwork (audiovisual subnetwork), but is also able to absorb implicit knowledge of emotions through two implicit knowledge-based injection subnetworks (K-injection subnetwork). In addition, it is trained with explicit features and implicit knowledge but can easily make inferences using only explicit features. We define the region of interest (ROI) visual features and Melspectrogram audio features as explicit features, which obviously are present in the raw audio-video data. On the other hand, we define the linguistic and acoustic emotional representations that do not exist in the audio-video data as implicit knowledge. The implicit knowledge distilled by adapting video situation descriptions and basic acoustic features (MFCCs, pitch and energy) to linguistic and acoustic K-injection subnetworks is defined as linguistic and acoustic knowledge, respectively. When compared to the baseline accuracy for the testing set of 47.88%, the average of the audiovisual models trained with the (linguistic, acoustic and linguistic-acoustic) K-injection subnetworks achieved an overall accuracy of 66.40%.

In the research field called connectomics, it is aimed to investigate the structure and connection of the neural system in the brain and sensory organ of the living things. Earlier studies have been proposed the method to help experts who suffer from labeling for three-dimensional reconstruction, that is important process to observe tiny neuronal structure in detail. In this paper, we proposed semi-supervised learning method, that performs pseudo-labeling. This makes it possible to automatically segment neuronal regions using only a small amount of labeled data. Experimental result showed that our method outperformed normal supervised learning with few labeled samples, while the accuracy was not sufficient yet.

In ambient information systems, not only extracting human behavior with a sensor network but also adaptive autonomous interaction between the environment and humans is an important function. In this paper, we propose a reinforcement learning methodology for acquiring suitable interaction for each person's daily behavior. This time, we used vital sensors to detect and classify a user's condition. In an experiment, we show the feasibility of the proposed methodology.

In recent years, highly-functional mobile devices such as smart phones and car navigation systems are widely used. These are important for our daily life because we use their applications anywhere and anytime. With the variety of applications available on these devices, however, it becomes more difficult to choose an appropriate application. Therefore we need a mechanism that recommends us suitable applications, which should depend on a user's context because he/she uses his/her devices differently in every context. This paper shows that it follows a power law what applications a user executes in daily life, and proposes a novel approach to find context-aware applications in the mobile devices. This approach is based on the term frequency - inverse document frequency (TF-IDF), which is used for extracting important keywords in a document. Moreover, we propose an application recommendation mechanism using this approach. Experimental results show that this recommendation mechanism is more effective than the mechanism using Naive Bayes.

This paper introduces a smart office chair, Owens Luis, whose pronunciation has a meaning of “an encouraging chair (****)” in Japanese. For most of the people, office environments are the place where they spend the longest time while awake. To improve the quality of life (QoL) in the office, Owens Luis monitors an office worker's mental and physiological states such as sleepiness and concentration, and controls the working environment by multi-modal displays including a motion chair, a variable color-temperature LED light and a hypersonic directional speaker.

In ambient information systems, not only extracting human behavior by sensor network but also adaptive autonomous interaction between the environment and humans is an important function. In this paper we propose a reinforcement learning framework to extract suitable interaction for each person from daily behavior. In the experiment, we show the feasibility of the proposed methodology.

We propose a smart office system that recognizes office workers' mental and physiological states to improve their quality of life at office. We integrated our systems into a single smart office environment. In this article we show the implementation of the smart office system and the details of each of its components such as I/O devices.

In this paper, we introduce the probabilistic awardee selection strategy, under which awardee is selected with a fixed probability, into the award phase of contract net protocol. We then point out that, by changing the probabilities in this strategy according the local workload, the overall performance can be considerably improved.

Data-centric affect modeling may render itself restrictive in practical applications for three reasons, namely, it falls short of feature optimization, infers discrete affect classes, and deals with relatively small to average sized datasets. Though it seems practical to use the feature combinations already associated to commonly investigated sensors, there may be other potentially optimal features that can lead to new relations. Secondly, although it seems more realistic to view affect as continuous, it requires using continuous labels that will increase the difficulty of modeling. Lastly, although a large scale dataset reflects a more precise range of values for any given feature, it severely hinders computational efficiency. We address these problems when inferring physiology-affect relations from datasets that contain 2-3 million feature vectors, each with 49 features and labelled with continuous affect values. We employ automatic feature selection to acquire near optimal feature subsets and a fast approximate kNN algorithm to solve the regression problem and cope with the challenge of a large scale dataset. Our results show that high estimation accuracy may be achieved even when the selected feature subset is only about 7% of the original features. May the results here motivate the HCI community to pursue affect modeling without being deterred by large datasets and further the discussions on acquiring optimal features for accurate continuous affect approximation.

Advanced Layer-3 (L3) switches achieve high-speed IP packet forwarding by storing parts of the header information from transmitted packets into the flow cache in the switch fabric when relaying the IP packets between subnets. When IP traffic is overloaded on an L3 switch, the flow cache is easily exhausted, decreasing the IP packet forwarding performance. Virtual LAN (VLAN), a virtualization technology at the data-link layer, is widely used for the internal networks of many organizations because it allows network configurations to be changed easily and provides design flexibility. In a VLAN-based local area network with multiple L3 switches, the relaying point for each VLAN can be placed on any of the L3 switches. We developed a new network control scheme called distributed virtual routing, which dynamically controls the packet exchange points for each VLAN to suppress the consumption of flow caches. We describe the basic concept and then evaluate the reduction of the relaying flows through the simulation using the real network data.

This paper describes how, in large-scale multi-agent systems, each agent's adaptive selection of peer agents for collaborative tasks affects the overall performance and how this performance varies with the workload of the system and with fluctuations

The basic framework of next generation intelligent transport systems (ITSs) is discussed. We propose a new congestion forecast system, which reacts to dynamically changing traffic conditions based on a coordination mechanism using pheromone communication models. We evaluate and verify the basic effectiveness of this method using simple simulations.

We describe a new method to estimate the relevance of two items (such as products and works of art) on the basis of the relationship between the corresponding user (blogger) groups on a blogspace, where a user group refers to a collection of users interested in an item. We estimated the strength of the relationship between user groups on the basis of their proximity on the blogspace. We validated our approach through experimental studies using actual data. In developing the method for estimating relevance among items, we introduced a new technique for measuring the proximity of two groups of vertices on a network, which can be thought of as an extension of conventional co-occurrence analysis.

We studied the problem of finding a subspace of Web pages that is contextually consistent for co-occurrence analysis. We looked at blogs and proposed blogger-based co-occurrence analysis, which assumes that two items are relevant to each other if they appear in any of the blog entries posted by the same blogger. We show that (1) blogger-based analysis outperforms conventional page-based analysis in solving context-sensitive problems and that (2) analysis focused on bloggers forming a community yields better performance compared with that focused on isolated bloggers.

The performance features of a massively multiagent system (MMAS) when applying the contract net protocol (CNP) are examined. The recent growth in the volume of e-commerce on the Internet is increasing the opportunities for coordinated transactions by agents, concurrently occurring everywhere. Because of limited CPU and network resources, running many interactive tasks among agents can lower the quality or efficiency of MMASs. Although CNP is a widely used negotiation protocol that can allocate tasks and resources to appropriate agents, it is unclear how effectively CNP works in an MMAS where thousands of agents work together and interfere with each other. The performance of CNP in such an MMAS, especially the overall efficiency and the reliability of promised completion times, is investigated by using an MAS simulation environment. The results show that only managerside control of CNP can improve performance in an MMAS.

The consideration of human feelings in automated music generation by intelligent music systems, albeit a compelling theme, has received very little attention. This work aims to computationally specify a system's music compositional intelligence that tightly couples with the listener's affective perceptions. First, the system induces a model that describes the relationship between feelings and musical structures. The model is learned by applying the inductive logic programming paradigm of FOIL coupled with the Diverse Density weighting metric over a dataset that was constructed using musical score fragments that were hand-labeled by the listener according to a semantic differential scale that uses bipolar affective descriptor pairs. A genetic algorithm, whose fitness function is based on the acquired model and follows basic music theory, is then used to generate variants of the original musical structures. Lastly, the system creates chordal and non-chordal tones out of the GA-obtained variants. Empirical results show that the system is 80.6% accurate at the average in classifying the affective labels of the musical structures and that it is able to automatically generate musical pieces that stimulate four kinds of impressions, namely, favorable-unfavorable, bright-dark, happy-sad, and heartrending-not heartrending.

HoME is a version of Smalltalk which can be efficiently executed on a multiprocessor and can be executed in parallel by combining a Smalltalk process with a Mach thread and executing the process on the thread. HoME is nearly the same as ordinary Smalltalk except that multiple processes may execute in parallel. Thus, almost all applications running on ordinary Smalltalk can be executed on HoME without changes in their code.