Zobrazeno 1 - 10
of 202
pro vyhledávání: '"Kim, Yunji"'
Continuously learning a variety of audio-video semantics over time is crucial for audio-related reasoning tasks in our ever-evolving world. However, this is a nontrivial problem and poses two critical challenges: sparse spatio-temporal correlation be
Externí odkaz:
http://arxiv.org/abs/2310.08204
Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions, where each text prompt provides a detailed description for a specific image region. To address this, we propose DenseDiffusion, a training-free meth
Externí odkaz:
http://arxiv.org/abs/2308.12964
Autor:
Kim, Doyeon, Ko, Eunji, Kim, Hyunsu, Kim, Yunji, Kim, Junho, Min, Dongchan, Kim, Junmo, Hwang, Sung Ju
Portrait stylization, which translates a real human face image into an artistically stylized image, has attracted considerable interest and many prior works have shown impressive quality in recent years. However, despite their remarkable performances
Externí odkaz:
http://arxiv.org/abs/2305.19135
Text-to-image diffusion models can generate diverse, high-fidelity images based on user-provided text prompts. Recent research has extended these models to support text-guided image editing. While text guidance is an intuitive editing interface for u
Externí odkaz:
http://arxiv.org/abs/2305.15779
Autor:
Lee, Jaewoong, Jang, Sangwon, Jo, Jaehyeong, Yoon, Jaehong, Kim, Yunji, Kim, Jin-Hwa, Ha, Jung-Woo, Hwang, Sung Ju
Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performance to diffusion-based models, their generation performance is still sub
Externí odkaz:
http://arxiv.org/abs/2304.01515
Text-to-image generation and image captioning are recently emerged as a new experimental paradigm to assess machine intelligence. They predict continuous quantity accompanied by their sampling techniques in the generation, making evaluation complicat
Externí odkaz:
http://arxiv.org/abs/2205.13445
Autor:
Kim, Yunji, Ha, Jung-Woo
Unsupervised fine-grained class clustering is a practical yet challenging task due to the difficulty of feature representations learning of subtle object details. We introduce C3-GAN, a method that leverages the categorical inference power of InfoGAN
Externí odkaz:
http://arxiv.org/abs/2112.14971
Publikováno v:
Energies (19961073). Jan2024, Vol. 17 Issue 1, p20. 13p.
We propose a deep video prediction model conditioned on a single image and an action class. To generate future frames, we first detect keypoints of a moving object and predict future motion as a sequence of keypoints. The input image is then translat
Externí odkaz:
http://arxiv.org/abs/1910.02027
This paper addresses the problem of manipulating images using natural language description. Our task aims to semantically modify visual attributes of an object in an image according to the text describing the new visual appearance. Although existing
Externí odkaz:
http://arxiv.org/abs/1810.11919