This work addresses the scarcity of high-quality, large-scale resources for Japanese Vision-and-Language (V&L) modeling. We present a scalable and reproducible pipeline that integrates large-scale web collection with rigorous filtering/deduplication, object-detection-driven evidence extraction, and Large Language Model (LLM)-based refinement under grounding constraints. Using this pipeline, we build two resources: an image-caption dataset (DEJIMA-Cap) and a VQA dataset (DEJIMA-VQA), each containing 3.88M image-text pairs, far exceeding the size of existing Japanese V&L datasets. Human evaluations demonstrate that DEJIMA achieves substantially higher Japaneseness and linguistic naturalness than datasets constructed via translation or manual annotation, while maintaining factual correctness at a level comparable to human-annotated corpora. Quantitative analyses of image feature distributions further confirm that DEJIMA broadly covers diverse visual domains characteristic of Japan, complementing its linguistic and cultural representativeness. Models trained on DEJIMA exhibit consistent improvements across multiple Japanese multimodal benchmarks, confirming that culturally grounded, large-scale resources play a key role in enhancing model performance. All data sources and modules in our pipeline are licensed for commercial use, and we publicly release the resulting dataset and metadata to encourage further research and industrial applications in Japanese V&L modeling.

For continuous action spaces, actor-critic methods are widely used in online reinforcement learning (RL). However, unlike RL algorithms for discrete actions, which generally model the optimal value function using the Bellman optimality operator, RL algorithms for continuous actions typically model Q-values for the current policy using the Bellman operator. These algorithms for continuous actions rely exclusively on policy updates for improvement, which often results in low sample efficiency. This study examines the effectiveness of incorporating the Bellman optimality operator into actor-critic frameworks. Experiments in a simple environment show that modeling optimal values accelerates learning but leads to overestimation bias. To address this, we propose an annealing approach that gradually transitions from the Bellman optimality operator to the Bellman operator, thereby accelerating learning while mitigating bias. Our method, combined with TD3 and SAC, significantly outperforms existing approaches across various locomotion and manipulation tasks, demonstrating improved performance and robustness to hyperparameters related to optimality. The code for this study is available at https://github.com/motokiomura/annealed-q-learning.

Human motion is inherently intentional, yet most motion modeling paradigms focus on low-level kinematics, overlooking the semantic and causal factors that drive behavior. Existing datasets further limit progress: they capture short, decontextualized actions in static scenes, providing little grounding for embodied reasoning. To address these limitations, we introduce $\textit{Intend to Move (I2M)}$, a large-scale, multimodal dataset for intention-grounded motion modeling. I2M contains 10.1 hours of two-person 3D motion sequences recorded in dynamic realistic home environments, accompanied by multi-view RGB-D video, 3D scene geometry, and language annotations of each participant’s evolving intentions. Benchmark experiments reveal a fundamental gap in current motion models: they fail to translate high-level goals into physically and socially coherent motion. I2M thus serves not only as a dataset but as a benchmark for embodied intelligence, enabling research on models that can reason about, predict, and act upon the ``why'' behind human motion.

In deep reinforcement learning, estimating the value function to evaluate the quality of states and actions is essential. The value function is often trained using the least squares method, which implicitly assumes a Gaussian error distribution. However, a recent study suggested that the error distribution for training the value function is often skewed because of the properties of the Bellman operator, and violates the implicit assumption of normal error distribution in the least squares method. To address this, we proposed a method called Symmetric Q-learning, in which the synthetic noise generated from a zero-mean distribution is added to the target values to generate a Gaussian error distribution. We evaluated the proposed method on continuous control benchmark tasks in MuJoCo. It improved the sample efficiency of a state-of-the-art reinforcement learning method by reducing the skewness of the error distribution.

The requirement for large labeled datasets is one of the limiting factors for training accurate deep neural networks. Unsupervised domain adaptation tackles this problem of limited training data by transferring knowledge from one domain, which has many labeled data, to a different domain for which little to no labeled data is available. One common approach is to learn domain-invariant features for example with an adversarial approach. Previous methods often train the domain classifier and label classifier network separately, where both classification networks have little interaction with each other. In this paper, we introduce a classifier-based backprop-induced weighting of the feature space. This approach has two main advantages. Firstly, it lets the domain classifier focus on features that are important for the classification, and, secondly, it couples the classification and adversarial branch more closely. Furthermore, we introduce an iterative label distribution alignment method, that employs results of previous runs to approximate a class-balanced dataloader. We conduct experiments and ablation studies on three benchmarks Office-31, Office-Home, and DomainNet to show the effectiveness of our proposed algorithm.

Writing a story is never easy. Even experienced writers sometimes unintentionally omit information from their writings, and it makes the stories not understandable from others. Complementing such unintentionally omitted information using a computer is helpful in providing writing support. Recently, in the field of story understanding and generation, story completion (SC) was proposed to generate the missing parts of an incomplete story. Although its applicability is limited because it requires that the user have prior knowledge of the missing part of a story, missing position prediction (MPP) can be used to compensate for this problem. MPP aims to predict the position of the missing part, but the prerequisite knowledge that “one sentence is missing” is still required. In this study, we propose Variable Number MPP (VN-MPP), a new MPP task that removes this restriction; that is, the task to predict multiple missing sentences or to judge whether there are no missing sentences in the first place. We also propose two methods for this new MPP task. One solves this task end-to-end, while the other learns the two modules separately. The latter allows the writer more flexibility in using the information by making the intermediate outputs between the modules explicit. Based on the novel task, we developed a creative writing support system, COMPASS. The results of a user experiment involving professional creators who write texts in Japanese confirm the efficacy and utility of the developed system. This study aimed to propose a creation support system and, at the same time, to build a relationship of trust between creators and researchers to lay the groundwork for future research and development of creation support AI.

Spherical images taken in all directions (360 degrees by 180 degrees) can represent an entire space including the subject, providing free direction viewing and an immersive experience to viewers. It is convenient and expands the usage scenarios to generate a spherical image from a few normal-field-of-view (NFOV) images, which are partial observations. The primary challenge is generating a plausible image and controlling the high degree of freedom involved in generating a wide area that includes all directions. We focus on scene symmetry, which is a basic property of the global structure of spherical images, such as the rotational and plane symmetries. We propose a method for generating a spherical image from a few NFOV images and controlling the generated regions using scene symmetry. We incorporate the intensity of the symmetry as a latent variable into conditional variational autoencoders to estimate the possible range of symmetry and decode a spherical image whose features are represented through a combination of symmetric transformations of the NFOV image features. Our experiments show that the proposed method can generate various plausible spherical images controlled from asymmetrically to symmetrically, and can reduce the reconstruction errors of the generated images based on the estimated symmetry.

Spiking neural networks (SNNs) can be run on neuromorphic devices with ultra-high speed and ultra-low energy consumption because of their binary and event-driven nature. Therefore, SNNs are expected to have various applications, including as generative models being running on edge devices to create high-quality images. In this study, we build a variational autoencoder (VAE) with SNN to enable image generation. VAE is known for its stability among generative models; recently, its quality advanced. In vanilla VAE, the latent space is represented as a normal distribution, and floating-point calculations are required in sampling. However, this is not possible in SNNs because all features must be binary time series data. Therefore, we constructed the latent space with an autoregressive SNN model, and randomly selected samples from its output to sample the latent variables. This allows the latent variables to follow the Bernoulli process and allows variational learning. Thus, we build the Fully Spiking Variational Autoencoder where all modules are constructed with SNN. To the best of our knowledge, we are the first to build a VAE only with SNN layers. We experimented with several datasets, and confirmed that it can generate images with the same or better quality compared to conventional ANNs. The code is available at https://github.com/kamata1729/FullySpikingVAE.

Spherical images taken in all directions (360 degrees by 180 degrees) allow the full surroundings of a subject to be represented, providing an immersive experience to viewers. Generating a spherical image from a single normal-field-of-view (NFOV) image is convenient and expands the usage scenarios considerably without relying on a specific panoramic camera or images taken from multiple directions; however, achieving such images remains a challenging and unresolved problem. The primary challenge is controlling the high degree of freedom involved in generating a wide area that includes all directions of the desired spherical image. We focus on scene symmetry, which is a basic property of the global structure of spherical images, such as rotational symmetry, plane symmetry, and asymmetry. We propose a method for generating a spherical image from a single NFOV image and controlling the degree of freedom of the generated regions using the scene symmetry. To estimate and control the scene symmetry using both a circular shift and flip of the latent image features, we incorporate the intensity of the symmetry as a latent variable into conditional variational autoencoders. Our experiments show that the proposed method can generate various plausible spherical images controlled from symmetric to asymmetric, and can reduce the reconstruction errors of the generated images based on the estimated symmetry.

The ability to estimate 3D object shape from a single image is vital to robotics and manufacturing. For instance, it enables iterative trial-and-error in simulated environments. In single-view reconstruction, implicit functions have demonstrated superior results over traditional methods. However, implicit functions suffer from the heavy computation of mesh extraction. This is due to the indirect mesh extraction, where the number of evaluation points grows cubically with resolution. On the other hand, reducing the resolution results in the discretization error of marching cubes (MC). In this work, we aim to perform efficient and accurate mesh extraction from implicit functions. The idea is to directly reconstruct the decision boundary of implicit functions as a mesh by reverse tracing from the output. It eliminates the need for evaluating massive points and error-prone MC. Consequently, we propose implementing an implicit function via a composite function of a flow and Binary-coded Input Neural Network (BCINN). The boundary of BCINN is easily identifiable, and the flow is invertible. Owing to these properties, the decision boundary of the composite function can be directly and efficiently reconstructed. In our experiments, we demonstrate that the proposed method significantly improves runtime/memory efficiency, with results comparable to those of existing methods. Specifically, our method enables real-time high-quality mesh inference from a single image.

The video understanding capability of video recognition models has been significantly improved by the development of deep learning techniques and various video datasets available. However, video recognition models are still vulnerable to invisible perturbations, which limits the use of deep video recognition models in the real world. We present a new benchmark for the robustness of action recognition classifiers to general corruptions, and show that a supervised contrastive learning framework is effective in obtaining discriminative and stable video representations, and makes deep video recognition models robust to general input corruptions. Experiments on the action recognition task for corrupted videos show the high robustness of the proposed method on the UCF101 and HMDB51 datasets with various common corruptions.

This study is aimed at finding a suitable method for generating time-series data such as video clips or avatar motions from text stating multiple events. This paper addresses the generation of variable-length time-series data considering the order and variable duration of events stated in the text. Although the use of the variant of Mean Squared Error (MSE) is a common means of training, only the gap between the element of ground-truth (GT) data and generated data at the same time are considered. Thus, variants of MSE are unsuitable for the task at hand because the loss may not be small for the generated and GT data with the same order of events if the time for each event does not overlap. To solve the problem, we propose a Dynamic Time Warping-Like method for Variable-Length data (DTWL-VL), which determines the corresponding elements of the GT and the generated data, allowing for the time difference between them, and makes them closer. We compared DTWL-VL, a variant of MSE, and an existing method for time-series data generation which considers the time difference between the corresponding part in the GT and generated data. Since the existing method is aimed at generating fixed-length data, we extend the method for generating variable-length time-series data. We conducted experiments using a dataset prepared for this study. Both DTWL-VL and the existing methods outperformed the MSE variant. Moreover, although the existing method outperformed DTWL-VL under certain settings, DTWL-VL required a smaller training period.

Reconstructing 3D objects from 2D images is a fundamental task in computer vision. Acurate structured reconstruction by parsimonious and semantic primitive representation further broadens its application. When reconstructing a target shape with multiple primitives, it is preferable that one can instantly access the union of basic properties of the shape such as collective volume and surface, treating the primitives as if they are one single shape. This becomes possible by primitive representation with unified implicit and explicit representations. However, primitive representations in current approaches do not satisfy all of the above requirements at the same time. To solve this problem, we propose a novel primitive representation named neural star domain (NSD) that learns primitive shapes in the star domain. We show that NSD is a universal approximator of the star domain and is not only parsimonious and semantic but also an implicit and explicit shape representation. We demonstrate that our approach outperforms existing methods in image reconstruction tasks, semantic capabilities, and speed and quality of sampling high-resolution meshes.

Many real-world systems involve interacting time series. The ability to detect causal dependencies between system components from observed time series of their outputs is essential for understanding system behavior. The quantification of causal influences between time series is based on the definition of some causality measure. Partial Canonical Correlation Analysis (Partial CCA) and its extensions are examples of methods used for robustly estimating the causal relationships between two multidimensional time series even when the time series are short. These methods assume that the input data are complete and have no missing values. However, real-world data often contain missing values. It is therefore crucial to estimate the causality measure robustly even when the input time series is incomplete. Treating this problem as a semi-supervised learning problem, we propose a novel semi-supervised extension of probabilistic Partial CCA called semi-Bayesian Partial CCA. Our method exploits the information in samples with missing values to prevent the overfitting of parameter estimation even when there are few complete samples. Experiments based on synthesized and real data demonstrate the ability of the proposed method to estimate causal relationships more correctly than existing methods when the data contain missing values, the dimensionality is large, and the number of samples is small.

Histopathological image analysis is an essential process for the discovery of diseases such as cancer. However, it is challenging to train CNN on whole slide images (WSIs) of gigapixel resolution considering the available memory capacity. Most of the previous works divide high resolution WSIs into small image patches and separately input them into the model to classify it as a tumor or a normal tissue. However, patch-based classification uses only patch-scale local information but ignores the relationship between neighboring patches. If we consider the relationship of neighboring patches and global features, we can improve the classification performance. In this paper, we propose a new model structure combining the patch-based classification model and whole slide-scale segmentation model in order to improve the prediction performance of automatic pathological diagnosis. We extract patch features from the classification model and input them into the segmentation model to obtain a whole slide tumor probability heatmap. The classification model considers patch-scale local features, and the segmentation model can take global information into account. We also propose a new optimization method that retains gradient information and trains the model partially for end-to-end learning with limited GPU memory capacity. We apply our method to the tumor/normal prediction on WSIs and the classification performance is improved compared with the conventional patch-based method.

Creativity is an essential element of human nature used for many activities, such as telling a story.Based on human creativity, researchers have attempted to teach a computer to generate stories automatically or support this creative process.In this study, we undertake the task of story ending generation.This is a relatively new task, in which the last sentence of a given incomplete story is automatically generated.This is challenging because, in order to predict an appropriate ending, the generation method should comprehend the context of events.Despite the importance of this task, no clear evaluation metric has been established thus far; hence, it has remained an open problem.Therefore, we study the various elements involved in evaluating an automatic method for generating story endings.First, we introduce a baseline hierarchical sequenceto-sequence method for story ending generation.Then, we conduct a pairwise comparison against human-written endings, in which annotators choose the preferable ending.In addition to a quantitative evaluation, we conduct a qualitative evaluation by asking annotators to specify the reason for their choice.From the collected reasons, we discuss what elements the evaluation should focus on, to thereby propose effective metrics for the task.

Kernel approximation methods are important tools for various machine learning problems. There are two major methods used to approximate the kernel function: the Nyström method and the random features method. However, the Nyström method requires relatively high-complexity post-processing to calculate a solution and the random features method does not provide sufficient generalization performance. In this paper, we propose a method that has good generalization performance without high-complexity postprocessing via empirical orthogonal decomposition using the probability distribution estimated from training data. We provide a bound for the approximation error of the proposed method. Our experiments show that the proposed method is better than the random features method and comparable with the Nyström method in terms of the approximation error and classification accuracy. We also show that hierarchical feature extraction using our kernel approximation demonstrates better performance than the existing methods.

Generating captions to describe images is a fundamental problem that combines computer vision and natural language processing. Recent works focus on descriptive phrases, such as "a white dog" to explain the visual composites of an input image. The phrases can not only express objects, attributes, events, and their relations but can also reduce visual complexity. A caption for an input image can be generated by connecting estimated phrases using a grammar model. However, because phrases are combinations of various words, the number of phrases is much larger than the number of single words. Consequently, the accuracy of phrase estimation suffers from too few training samples per phrase. In this paper, we propose a novel phrase-learning method: Common Subspace for Model and Similarity (CoSMoS). In order to overcome the shortage of training samples, CoSMoS obtains a subspace in which (a) all feature vectors associated with the same phrase are mapped as mutually close, (b) classifiers for each phrase are learned, and (c) training samples are shared among co-occurring phrases. Experimental results demonstrate that our system is more accurate than those in earlier work and that the accuracy increases when the dataset from the web increases.

Histogram of Oriented Gradients (HOG) [1] descriptors have been widely used for object detection. An important limitation is that these descriptors tend to vary considerably when objects are horizontally flipped, as is often the case. We propose novel MI-HOG descriptors that are obtained by transforming HOG descriptors to be invariant to mirror reflection. In their extraction process, we consider not only the transform of independent elements but also the combination of those in different location and in orientation, which yields better performance. We showed a greater than 10 % increase in average precision compared to HOG descriptors.

Partial canonical correlation analysis (partial CCA) is a statistical method that estimates a pair of linear projections onto a low dimensional space, where the correlation between two multidimensional variables is maximized after eliminating the influence of a third variable. Partial CCA is known to be closely related to a causality measure between two time series. However, partial CCA requires the inverses of covariance matrices, so the calculation is not stable. This is particularly the case for high-dimensional data or small sample sizes. Additionally, we cannot estimate the optimal dimension of the subspace in the model. In this paper, we have addressed these problems by proposing a probabilistic interpretation of partial CCA and deriving a Bayesian estimation method based on the probabilistic model. Our numerical experiments demonstrated that our methods can stably estimate the model parameters, even in high dimensions or when there are a small number of samples.