Zobrazeno 1 - 10
of 318
pro vyhledávání: '"Cai, Yujun"'
To facilitate the application of motion prediction in practice, recently, the few-shot motion prediction task has attracted increasing research attention. Yet, in existing few-shot motion prediction works, a specific model that is dedicatedly trained
Externí odkaz:
http://arxiv.org/abs/2405.15267
Recently, Gaussian Splatting, a method that represents a 3D scene as a collection of Gaussian distributions, has gained significant attention in addressing the task of novel view synthesis. In this paper, we highlight a fundamental limitation of Gaus
Externí odkaz:
http://arxiv.org/abs/2405.15196
Skeleton-based action recognition has attracted lots of research attention. Recently, to build an accurate skeleton-based action recognizer, a variety of works have been proposed. Among them, some works use large model architectures as backbones of t
Externí odkaz:
http://arxiv.org/abs/2404.00532
Estimating the 6D object pose from a single RGB image often involves noise and indeterminacy due to challenges such as occlusions and cluttered backgrounds. Meanwhile, diffusion models have shown appealing performance in generating high-quality image
Externí odkaz:
http://arxiv.org/abs/2401.00029
In this paper, we propose a novel generative model that utilizes a conditional Energy-Based Model (EBM) for enhancing Variational Autoencoder (VAE), termed Energy-Calibrated VAE (EC-VAE). Specifically, VAEs often suffer from blurry generated samples
Externí odkaz:
http://arxiv.org/abs/2311.04071
Instruction-tuned large language models (LLMs), such as ChatGPT, have led to promising zero-shot performance in discriminative natural language understanding (NLU) tasks. This involves querying the LLM using a prompt containing the question, and the
Externí odkaz:
http://arxiv.org/abs/2310.13206
Open-set object recognition aims to identify if an object is from a class that has been encountered during training or not. To perform open-set object recognition accurately, a key challenge is how to reduce the reliance on spurious-discriminative fe
Externí odkaz:
http://arxiv.org/abs/2309.12780
Autor:
Wang, Yiwei, Hooi, Bryan, Wang, Fei, Cai, Yujun, Liang, Yuxuan, Zhou, Wenxuan, Tang, Jing, Duan, Manjuan, Chen, Muhao
Relation extraction (RE) aims to extract the relations between entity names from the textual context. In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations reflected by
Externí odkaz:
http://arxiv.org/abs/2305.13551
Autor:
Han, Shangchen, Wu, Po-chen, Zhang, Yubo, Liu, Beibei, Zhang, Linguang, Wang, Zheng, Si, Weiguang, Zhang, Peizhao, Cai, Yujun, Hodan, Tomas, Cabezas, Randi, Tran, Luan, Akbay, Muzaffer, Yu, Tsz-Ho, Keskin, Cem, Wang, Robert
Real-time tracking of 3D hand pose in world space is a challenging problem and plays an important role in VR interaction. Existing work in this space are limited to either producing root-relative (versus world space) 3D pose or rely on multiple stage
Externí odkaz:
http://arxiv.org/abs/2211.00099
For tackling the task of 2D human pose estimation, the great majority of the recent methods regard this task as a heatmap estimation problem, and optimize the heatmap prediction using the Gaussian-smoothed heatmap as the optimization objective and us
Externí odkaz:
http://arxiv.org/abs/2210.00740