Výsledky vyhledávání - "Uchida, Kengo"

Report

MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training

Autor: Uchida, Kengo, Shibuya, Takashi, Takida, Yuhta, Murata, Naoki, Takahashi, Shusuke, Mitsufuji, Yuki

In motion generation, controllability as well as generation quality and speed is becoming more and more important. There are various motion editing tasks, such as in-betweening, upper body editing, and path-following, but existing methods perform mot

Externí odkaz: http://arxiv.org/abs/2406.01867

Zobrazit plný text záznamu

Report

HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes

Autor: Takida, Yuhta, Ikemiya, Yukara, Shibuya, Takashi, Shimada, Kazuki, Choi, Woosung, Lai, Chieh-Hsin, Murata, Naoki, Uesaka, Toshimitsu, Uchida, Kengo, Liao, Wei-Hsiang, Mitsufuji, Yuki

Vector quantization (VQ) is a technique to deterministically learn features with discrete codebook representations. It is commonly performed with a variational autoencoding model, VQ-VAE, which can be further extended to hierarchical structures for m

Externí odkaz: http://arxiv.org/abs/2401.00365

Zobrazit plný text záznamu

Report

Zero- and Few-shot Sound Event Localization and Detection

Autor: Shimada, Kazuki, Uchida, Kengo, Koyama, Yuichiro, Shibuya, Takashi, Takahashi, Shusuke, Mitsufuji, Yuki, Kawahara, Tatsuya

Sound event localization and detection (SELD) systems estimate direction-of-arrival (DOA) and temporal activation for sets of target classes. Neural network (NN)-based SELD systems have performed well in various sets of target classes, but they only

Externí odkaz: http://arxiv.org/abs/2309.09223

Zobrazit plný text záznamu

Report

STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events

Autor: Shimada, Kazuki, Politis, Archontis, Sudarsanam, Parthasaarathy, Krause, Daniel, Uchida, Kengo, Adavanne, Sharath, Hakala, Aapo, Koyama, Yuichiro, Takahashi, Naoya, Takahashi, Shusuke, Virtanen, Tuomas, Mitsufuji, Yuki

While direction of arrival (DOA) of sound events is generally estimated from multichannel audio data recorded in a microphone array, sound events usually derive from visually perceptible source objects, e.g., sounds of footsteps come from the feet of

Externí odkaz: http://arxiv.org/abs/2306.09126

Zobrazit plný text záznamu