Zobrazeno 1 - 10
of 9 881
pro vyhledávání: '"Lee, Seong"'
Autor:
Ramakrishnan, Vandana, Lee, Kyoung-Soo, Artale, Maria Celeste, Yang, Eric Gawiser. Yujin, Park, Changbom, Ciardullo, Robin, Guaita, Lucia, Im, Sang Hyeok, Kim, Seongjae, Kumar, Ankit, Lee, Jaehyun, Lee, Seong-Kook, Moon, Byeongha, Padilla, Nelson, Pope, Alexandra, Popescu, Roxana, Song, Hyunmi, Troncoso, Paulina, Valdes, Francisco, Zabludoff, Ann
To understand the formation and evolution of massive cosmic structures, studying them at high redshift, in the epoch when they formed the majority of their mass is essential. The One-hundred-deg$^2$ DECam Imaging in Narrowbands (ODIN) survey is under
Externí odkaz:
http://arxiv.org/abs/2406.08645
Despite rapid advances in the field of emotional text-to-speech (TTS), recent studies primarily focus on mimicking the average style of a particular emotion. As a result, the ability to manipulate speech emotion remains constrained to several predefi
Externí odkaz:
http://arxiv.org/abs/2406.07803
As e-commerce expands, delivering real-time personalized recommendations from vast catalogs poses a critical challenge for retail platforms. Maximizing revenue requires careful consideration of both individual customer characteristics and available i
Externí odkaz:
http://arxiv.org/abs/2404.17592
In this paper, we investigate that the normalized coordinate expression is a key factor as reliance on hand-crafted components in query-based detectors for temporal action detection (TAD). Despite significant advancements towards an end-to-end framew
Externí odkaz:
http://arxiv.org/abs/2404.02405
We propose a robust method for point cloud registration that can handle both unknown scales and extreme outlier ratios. Our method, dubbed PCR-99, uses a deterministic 3-point sampling approach with two novel mechanisms that significantly boost the s
Externí odkaz:
http://arxiv.org/abs/2402.16598
Explaining generative diffusion models via visual analysis for interpretable decision-making process
Publikováno v:
Expert Systems with Applications 248 (2024) 123231
Diffusion models have demonstrated remarkable performance in generation tasks. Nevertheless, explaining the diffusion process remains challenging due to it being a sequence of denoising noisy images that are difficult for experts to interpret. To add
Externí odkaz:
http://arxiv.org/abs/2402.10404
This paper discusses an investigation on a novel hydraulic pump concept. The idea aims on a pump principle to be directly connected to high-speed electric motors to build compact high-pressure drives. The pump can theoretically work without solid con
Externí odkaz:
https://tud.qucosa.de/id/qucosa%3A71110
https://tud.qucosa.de/api/qucosa%3A71110/attachment/ATT-0/
https://tud.qucosa.de/api/qucosa%3A71110/attachment/ATT-0/
Many multi-object tracking (MOT) approaches, which employ the Kalman Filter as a motion predictor, assume constant velocity and Gaussian-distributed filtering noises. These assumptions render the Kalman Filter-based trackers effective in linear motio
Externí odkaz:
http://arxiv.org/abs/2401.13950
Autor:
Lim, Byoungsung, Lee, Seong-Whan
Recent advances in implicit function-based approaches have shown promising results in 3D human reconstruction from a single RGB image. However, these methods are not sufficient to extend to more general cases, often generating dragged or disconnected
Externí odkaz:
http://arxiv.org/abs/2401.14565
Autor:
Jo, Hayoung, Lee, Seong-Whan
With the rapid advancement in cyber-physical systems, the increasing number of sensors has significantly complicated manual monitoring of system states. Consequently, graph-based time-series anomaly detection methods have gained attention due to thei
Externí odkaz:
http://arxiv.org/abs/2401.13872