Zobrazeno 1 - 10
of 116
pro vyhledávání: '"Park, Seongsik"'
Autor:
Jeong, Dayena, Park, Jaewoo, Jo, Jeonghee, Park, Jongkil, Kim, Jaewook, Jang, Hyun Jae, Lee, Suyoun, Park, Seongsik
Recent deep neural networks (DNNs), such as diffusion models [1], have faced high computational demands. Thus, spiking neural networks (SNNs) have attracted lots of attention as energy-efficient neural networks. However, conventional spiking neurons,
Externí odkaz:
http://arxiv.org/abs/2409.00044
Publikováno v:
Applied Sciences 2024, 14(19), 8710
Recently, vision Transformers (ViTs) have been actively applied to fine-grained visual recognition (FGVR). ViT can effectively model the interdependencies between patch-divided object regions through an inherent self-attention mechanism. In addition,
Externí odkaz:
http://arxiv.org/abs/2308.02161
Autor:
Park, Seongsik, Jo, Jeonghee, Park, Jongkil, Jeong, Yeonjoo, Kim, Jaewook, Lee, Suyoun, Kwak, Joon Young, Kim, Inho, Park, Jong-Keuk, Lee, Kyeong Seok, Hwang, Gye Weon, Jang, Hyun Jae
Deep spiking neural networks (SNNs) are promising neural networks for their model capacity from deep neural network architecture and energy efficiency from SNNs' operations. To train deep SNNs, recently, spatio-temporal backpropagation (STBP) with su
Externí odkaz:
http://arxiv.org/abs/2308.00558
Autor:
Moon, Jiyong, Park, Seongsik
One of the key issues in facial expression recognition in the wild (FER-W) is that curating large-scale labeled facial images is challenging due to the inherent complexity and ambiguity of facial images. Therefore, in this paper, we propose a self-su
Externí odkaz:
http://arxiv.org/abs/2303.07648
Publikováno v:
The IEEE / CVF Computer Vision and Pattern Recognition Conference 2022
Event cameras respond to brightness changes in the scene asynchronously and independently for every pixel. Due to the properties, these cameras have distinct features: high dynamic range (HDR), high temporal resolution, and low power consumption. How
Externí odkaz:
http://arxiv.org/abs/2206.07578
Spiking neural networks (SNNs) that mimic information transmission in the brain can energy-efficiently process spatio-temporal information through discrete and sparse spikes, thereby receiving considerable attention. To improve accuracy and energy ef
Externí odkaz:
http://arxiv.org/abs/2201.12738
Publikováno v:
In Knowledge-Based Systems 20 December 2024 306
Autor:
Na, Byunggook, Jang, Jaehee, Park, Seongsik, Kim, Seijoon, Kim, Joonoo, Jeong, Moon Sik, Kim, Kwang Choon, Heo, Seon, Kim, Yoonsang, Yoon, Sungroh
Various deep learning applications on smartphones have been rapidly rising, but training deep neural networks (DNNs) has too large computational burden to be executed on a single smartphone. A portable cluster, which connects smartphones with a wirel
Externí odkaz:
http://arxiv.org/abs/2110.12172
Autor:
Park, Seongsik, Kim, Harksoo
Sentence-level relation extraction mainly aims to classify the relation between two entities in a sentence. The sentence-level relation extraction corpus often contains data that are difficult for the model to infer or noise data. In this paper, we p
Externí odkaz:
http://arxiv.org/abs/2107.09332
Spiking neural networks (SNNs) have been gaining interest as energy-efficient alternatives of conventional artificial neural networks (ANNs) due to their event-driven computation. Considering the future deployment of SNN models to constrained neuromo
Externí odkaz:
http://arxiv.org/abs/2106.07172