Searcharxiv⌕ Search

arXiv subjects

Masahiro Toyoura

Publications and source records attributed to Masahiro Toyoura.

5 recordsLinked to original sources

Small Data in Long-Term Environmental Vision: Annotation Noise, Gamification, and Label-Budget Scaling

Long-running environmental camera networks produce abundant images but few reliable annotations. Using FujiView, a network of webcams around Mount Fuji, we study three linked questions: whether gamification affects annotation participation and agreement, how annotators disagree on ordinal visibility labels, and how label budget affects downstream classification. Across seven nonrandomized sessions with 22 labelers, gamification showed a more promising pattern for sustained participation than for labeling speed or agreement. In the closest remote-session comparison, the session recorded as gamified had longer active labeling time, while throughput and reference agreement remained similar. Annotation disagreement was substantial at fine granularity: crowd votes matched the single-annotator reference on 49.1% of exact visibility classes, versus 90.2% after grouping them into Good/Poor. In five-replicate label-budget experiments, models using 25% of the available label pool achieved held-out exact accuracy only 2.8 percentage points below the full-pool model on average. Together, these findings highlight the importance of designing reliable annotation targets, evaluating engagement mechanisms without assuming causal benefits, and using empirical scaling curves to plan labeling effort.

cs.CV↗

Different Timescales, Different Signals: Multimodal Landmark-Visibility Prediction in a Long-Term Webcam Network

Scenic visibility is not a single forecasting problem: planning a trip months ahead, deciding whether to go outside today, and judging whether tomorrow will be clear rely on different information. Using a year-scale multimodal archive of Mount Fuji webcams and meteorological observations, we identify a clear hierarchy across timescales. Seasonal climatology provides useful long-range guidance, webcam imagery is the strongest same-day observation (AUC 0.95), and the numerical forecast valid on the target day carries most of the day-specific signal one to three days ahead. Revealing this hierarchy requires evaluation that respects the dependence among cameras observing the same regional weather state: permissive splits substantially overstate multi-day performance, while date-grouped and forward-in-time evaluation reduce the apparent contribution of the current scene and current weather. On 6,575 camera-days, the current visual summary provides no measurable one-day gain once the target-day forecast is available. The remaining opportunity lies at shorter horizons, where the present visual representation discards cloud geometry and motion. These results recast scenic visibility prediction as a multi-timescale sensing problem rather than a single multimodal forecasting task.

cs.CV↗

Wavelet Integrated Convolutional Neural Network for ECG Signal Denoising

Wearable electrocardiogram (ECG) measurement using dry electrodes has a problem with high-intensity noise distortion. Hence, a robust noise reduction method is required. However, overlapping frequency bands of ECG and noise make noise reduction difficult. Hence, it is necessary to provide a mechanism that changes the characteristics of the noise based on its intensity and type. This study proposes a convolutional neural network (CNN) model with an additional wavelet transform layer that extracts the specific frequency features in a clean ECG. Testing confirms that the proposed method effectively predicts accurate ECG behavior with reduced noise by accounting for all frequency domains. In an experiment, noisy signals in the signal-to-noise ratio (SNR) range of -10-10 are evaluated, demonstrating that the efficiency of the proposed method is higher when the SNR is small.

eess.SP↗

LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering

A key challenge in the task of human pose and shape estimation is occlusion, including self-occlusions, object-human occlusions, and inter-person occlusions. The lack of diverse and accurate pose and shape training data becomes a major bottleneck, especially for scenes with occlusions in the wild. In this paper, we focus on the estimation of human pose and shape in the case of inter-person occlusions, while also handling object-human occlusions and self-occlusion. We propose a novel framework that synthesizes occlusion-aware silhouette and 2D keypoints data and directly regress to the SMPL pose and shape parameters. A neural 3D mesh renderer is exploited to enable silhouette supervision on the fly, which contributes to great improvements in shape estimation. In addition, keypoints-and-silhouette-driven training data in panoramic viewpoints are synthesized to compensate for the lack of viewpoint diversity in any existing dataset. Experimental results show that we are among the state-of-the-art on the 3DPW and 3DPW-Crowd datasets in terms of pose estimation accuracy. The proposed method evidently outperforms Mesh Transformer, 3DCrowdNet and ROMP in terms of shape estimation. Top performance is also achieved on SSP-3D in terms of shape prediction accuracy. Demo and code will be available at https://igame-lab.github.io/LASOR/.

cs.CV↗

Image-based Textile Decoding

A textile fabric consists of countless parallel vertical yarns (warps) and horizontal yarns (wefts). While common looms can weave repetitive patterns, Jacquard looms can weave the patterns without repetition restrictions. A pattern in which the warps and wefts cross on a grid is defined in a binary matrix. The binary matrix can define which warp and weft is on top at each grid point of the Jacquard fabric. The process can be regarded as encoding from pattern to textile. In this work, we propose a decoding method that generates a binary pattern from a textile fabric that has been already woven. We could not use a deep neural network to learn the process based solely on the training set of patterns and observed fabric images. The crossing points in the observed image were not completely located on the grid points, so it was difficult to take a direct correspondence between the fabric images and the pattern represented by the matrix in the framework of deep learning. Therefore, we propose a method that can apply the framework of deep learning via the intermediate representation of patterns and images. We show how to convert a pattern into an intermediate representation and how to reconvert the output into a pattern and confirm its effectiveness. In this experiment, we confirmed that 93% of correct pattern was obtained by decoding the pattern from the actual fabric images and weaving them again.

cs.CV↗