Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Baek, Seungryul"'
This paper introduces the first text-guided work for generating the sequence of hand-object interaction in 3D. The main challenge arises from the lack of labeled data where existing ground-truth datasets are nowhere near generalizable in interaction
Externí odkaz:
http://arxiv.org/abs/2404.00562
Autor:
Fan, Zicong, Ohkawa, Takehiko, Yang, Linlin, Lin, Nie, Zhou, Zhishan, Zhou, Shihao, Liang, Jiajun, Gao, Zhong, Zhang, Xuanyang, Zhang, Xue, Li, Fei, Liu, Zheng, Lu, Feng, Zeid, Karim Abou, Leibe, Bastian, On, Jeongwan, Baek, Seungryul, Prakash, Aditya, Gupta, Saurabh, He, Kun, Sato, Yoichi, Hilliges, Otmar, Chang, Hyung Jin, Yao, Angela
We interact with the world with our hands and see it through our own (egocentric) perspective. A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation.
Externí odkaz:
http://arxiv.org/abs/2403.16428
This paper presents a new approach for the detection of fake videos, based on the analysis of style latent vectors and their abnormal behavior in temporal changes in the generated videos. We discovered that the generated facial videos suffer from the
Externí odkaz:
http://arxiv.org/abs/2403.06592
In the field of Class Incremental Object Detection (CIOD), creating models that can continuously learn like humans is a major challenge. Pseudo-labeling methods, although initially powerful, struggle with multi-scenario incremental learning due to th
Externí odkaz:
http://arxiv.org/abs/2403.05346
In the field of class incremental learning (CIL), generative replay has become increasingly prominent as a method to mitigate the catastrophic forgetting, alongside the continuous improvements in generative models. However, its application in class i
Externí odkaz:
http://arxiv.org/abs/2402.17323
Autor:
Cha, Junuk, Lee, Hansol, Kim, Jaewon, Truong, Nhat Nguyen Bao, Yoon, Jae Shin, Baek, Seungryul
This paper introduces a novel pipeline to reconstruct the geometry of interacting multi-person in clothing on a globally coherent scene space from a single image. The main challenge arises from the occlusion: a part of a human body is not visible fro
Externí odkaz:
http://arxiv.org/abs/2401.06415
The appearance of a human in clothing is driven not only by the pose but also by its temporal context, i.e., motion. However, such context has been largely neglected by existing monocular human modeling methods whose neural networks often struggle to
Externí odkaz:
http://arxiv.org/abs/2312.16842
Class-Wise Buffer Management for Incremental Object Detection: An Effective Buffer Training Strategy
Autor:
Kim, Junsu, Hong, Sumin, Kim, Chanwoo, Kim, Jihyeon, Tiruneh, Yihalem Yimolal, On, Jeongwan, Song, Jihyun, Choi, Sunhwa, Baek, Seungryul
Class incremental learning aims to solve a problem that arises when continuously adding unseen class instances to an existing model This approach has been extensively studied in the context of image classification; however its applicability to object
Externí odkaz:
http://arxiv.org/abs/2312.09139
Single-stage multi-person human pose estimation (MPPE) methods have shown great performance improvements, but existing methods fail to disentangle features by individual instances under crowded scenes. In this paper, we propose a bounding box-level i
Externí odkaz:
http://arxiv.org/abs/2309.14072
Reenacting facial images is an important task that can find numerous applications. We proposed IFaceUV, a fully differentiable pipeline that properly combines 2D and 3D information to conduct the facial reenactment task. The three-dimensional morphab
Externí odkaz:
http://arxiv.org/abs/2306.04957