Zobrazeno 1 - 10
of 272
pro vyhledávání: '"Liu, Hanbing"'
Addressing the large distribution gap between training and testing data has long been a challenge in machine learning, giving rise to fields such as transfer learning and domain adaptation. Recently, Continuous Domain Adaptation (CDA) has emerged as
Externí odkaz:
http://arxiv.org/abs/2402.16681
Autor:
Li, Haoyang, Zhang, Jing, Liu, Hanbing, Fan, Ju, Zhang, Xiaokang, Zhu, Jun, Wei, Renjie, Pan, Hongyan, Li, Cuiping, Chen, Hong
Language models have shown promising performance on the task of translating natural language questions into SQL queries (Text-to-SQL). However, most of the state-of-the-art (SOTA) approaches rely on powerful yet closed-source large language models (L
Externí odkaz:
http://arxiv.org/abs/2402.16347
Autor:
Liu, Hanbing, Xiang, Wangmeng, He, Jun-Yan, Cheng, Zhi-Qi, Luo, Bin, Geng, Yifeng, Xie, Xuansong
Accurately estimating the 3D pose of humans in video sequences requires both accuracy and a well-structured architecture. With the success of transformers, we introduce the Refined Temporal Pyramidal Compression-and-Amplification (RTPCA) transformer.
Externí odkaz:
http://arxiv.org/abs/2309.01365
Autor:
Liu, Hanbing, He, Jun-Yan, Cheng, Zhi-Qi, Xiang, Wangmeng, Yang, Qize, Chai, Wenhao, Wang, Gaoang, Bao, Xu, Luo, Bin, Geng, Yifeng, Xie, Xuansong
Existing 3D human pose estimators face challenges in adapting to new datasets due to the lack of 2D-3D pose pairs in training sets. To overcome this issue, we propose \textit{Multi-Hypothesis \textbf{P}ose \textbf{Syn}thesis \textbf{D}omain \textbf{A
Externí odkaz:
http://arxiv.org/abs/2308.09678
Autor:
Bao, Xu, Cheng, Zhi-Qi, He, Jun-Yan, Li, Chenyang, Xiang, Wangmeng, Sun, Jingdong, Liu, Hanbing, Liu, Wei, Luo, Bin, Geng, Yifeng, Xie, Xuansong
Accurate facial landmark detection is critical for facial analysis tasks, yet prevailing heatmap and coordinate regression methods grapple with prohibitive computational costs and quantization errors. Through comprehensive theoretical analysis and ex
Externí odkaz:
http://arxiv.org/abs/2305.16437
Autor:
Chen, Sibei, Liu, Hanbing, Jin, Weiting, Sun, Xiangyu, Feng, Xiaoyao, Fan, Ju, Du, Xiaoyong, Tang, Nan
Orchestrating a high-quality data preparation program is essential for successful machine learning (ML), but it is known to be time and effort consuming. Despite the impressive capabilities of large language models like ChatGPT in generating programs
Externí odkaz:
http://arxiv.org/abs/2304.03540
Autor:
Chen, Hanyuan, He, Jun-Yan, Xiang, Wangmeng, Cheng, Zhi-Qi, Liu, Wei, Liu, Hanbing, Luo, Bin, Geng, Yifeng, Xie, Xuansong
Publikováno v:
In the 32nd international Joint Conference on Artificial Intelligence (IJCAI 2023)
Human pose estimation is a challenging task due to its structured data sequence nature. Existing methods primarily focus on pair-wise interaction of body joints, which is insufficient for scenarios involving overlapping joints and rapidly changing po
Externí odkaz:
http://arxiv.org/abs/2302.01825
For linear control systems, the usual state feedback stabilizability has two components: one is a continuous observation mode (i.e., to observe solutions continuously in time), and the other is a class of feedback laws (which is usually the space of
Externí odkaz:
http://arxiv.org/abs/2208.12728
Autor:
Chen, Yanqiu, Huang, Xinxin, Wang, Guang, Liu, Hanbing, Lin, Xixiang, Song, Pingan, Zhou, Wenrui, Luo, Jianlin, Gao, Qiang
Publikováno v:
In Chemical Engineering Journal 15 July 2024 492
Publikováno v:
In Ecological Indicators July 2024 164