14 accepted papers
Large vision–language models (VLMs) deliver state-of-the-art results on a wide range of multimodal tasks, yet they remain prone to visual hallucinations, producing content that is not grounded in the input image. Despite progress with visual supervision, reinforcement learning, and post-hoc attenti…
We present Subtractive Training<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>, a simple and novel method for synthesizing individual musical instrument stems given other instruments as context. This method pairs a dataset of complete music mixe…
We present a new multi-modal face image generation method that converts a text prompt and a visual input such as a semantic mask or scribble map into a photo-realistic face image. To do this we combine the strengths of Generative Adversarial networks (GANs) and diffusion models (DMs) by employing th…
Existing techniques for image-to-image translation commonly have suffered from two critical problems: heavy reliance on per-sample domain annotation and/or inability to handle multiple attributes per image. Recent truly-unsupervised methods adopt clustering approaches to easily provide per-sample on…
Multi-resolution hash encoding has recently been proposed to reduce the computational cost of neural renderings, such as NeRF. This method requires accurate camera poses for the neural renderings of given scenes. However, contrary to previous methods jointly optimizing camera poses and 3D scenes, th…
Recent techniques to solve photorealistic style transfer within deep convolutional neural networks (CNNs) generally require intensive training from large-scale datasets, thus having limited applicability and poor generalization ability to unseen images or styles. To overcome this, we propose a novel…
We present a novel Transformer-based network architecture for instance-aware image-to-image translation, dubbed InstaFormer, to effectively integrate global- and instance-level information. By considering extracted content features from an image as tokens, our networks discover global consensus of c…
Volumetric deep learning approach towards stereo matching aggregates a cost volume computed from input left and right images using 3D convolutions. Recent works showed that utilization of extracted image features and a spatially varying cost volume aggregation complements 3D convolutions. However, e…
In this letter, using the active dual-mode twisted string actuation (TSA) mechanism and tiny tension sensors on the tendon strings, an anthropomorphic robot hand is newly designed in a compact manner. Thanks to the active dual-mode TSA mechanism, which is a miniaturized transmission, the proposed ro
This paper presents a modified nonlinear pneumatic model for pneumatic force servo systems. The modified model is proposed in order to estimate pressures accurately for both chambers of a pneumatic cylinder by adopting flow coefficient maps, which is different from a conventional model whose flow co…
Electrotactile stimulation has been used to provide sensory information of forearm prosthesis to users. Although conventional sensory feedback method, where one electrode expresses sensory information of only one finger, could provide force information of three fingers by using three electrodes, it…
In this paper, a dual-mode twisting actuation mechanism with an active clutch is newly presented for a high performance tendon-driven robot (e.g., robot hand). This mechanism is a kind of mechanical automatic power transmission mechanism which provides fast motion and large contraction force by two…
When designing a lower-limb assisting robot with body-weight support (BWS), it is important to achieve high force fidelity to support body weight at standing phase. Low impedance operation at swing phase is also required not to disturb leg motions for users. The SoftGait is designed to achieve both…
In this paper, a method to extract the fingertip forces of the index and middle fingers from surface electromyography (sEMG) signals is studied by adopting the known common spatial pattern (CSP) approach. For unsupervised estimation of fingertip forces in real-time, CSP filtering is shown to be a no…