Zobrazeno 1 - 10
of 2 713
pro vyhledávání: '"LING Hao"'
This research delves into the problem of interactive editing of human motion generation. Previous motion diffusion models lack explicit modeling of the word-level text-motion correspondence and good explainability, hence restricting their fine-graine
Externí odkaz:
http://arxiv.org/abs/2410.18977
Autor:
Chen, Ling-Hao, Lu, Shunlin, Zeng, Ailing, Zhang, Hao, Wang, Benyou, Zhang, Ruimao, Zhang, Lei
This study delves into the realm of multi-modality (i.e., video and motion modalities) human behavior understanding by leveraging the powerful capabilities of Large Language Models (LLMs). Diverging from recent LLMs designed for video-only or motion-
Externí odkaz:
http://arxiv.org/abs/2405.20340
This work introduces MotionLCM, extending controllable motion generation to a real-time level. Existing methods for spatial-temporal control in text-conditioned motion generation suffer from significant runtime inefficiency. To address this issue, we
Externí odkaz:
http://arxiv.org/abs/2404.19759
Autor:
Li, Yunshui, Hui, Binyuan, Xia, Xiaobo, Yang, Jiaxi, Yang, Min, Zhang, Lei, Si, Shuzheng, Chen, Ling-Hao, Liu, Junhao, Liu, Tongliang, Huang, Fei, Li, Yongbin
Contemporary practices in instruction tuning often hinge on enlarging data scaling without a clear strategy for ensuring data quality, inadvertently introducing noise that may compromise model performance. To address this challenge, we introduce \tex
Externí odkaz:
http://arxiv.org/abs/2312.10302
Autor:
Chen, Ling-Hao, Zhang, Yuanshuo, Huang, Taohua, Su, Liangcai, Lin, Zeyi, Xiao, Xi, Xia, Xiaobo, Liu, Tongliang
Deep learning has achieved remarkable success in graph-related tasks, yet this accomplishment heavily relies on large-scale high-quality annotated datasets. However, acquiring such datasets can be cost-prohibitive, leading to the practical use of lab
Externí odkaz:
http://arxiv.org/abs/2312.08852
Autor:
Lu, Shunlin, Chen, Ling-Hao, Zeng, Ailing, Lin, Jing, Zhang, Ruimao, Zhang, Lei, Shum, Heung-Yeung
This work targets a novel text-driven whole-body motion generation task, which takes a given textual description as input and aims at generating high-quality, diverse, and coherent facial expressions, hand gestures, and body motions simultaneously. P
Externí odkaz:
http://arxiv.org/abs/2310.12978
Autor:
Zhang, Shaokun, Xia, Xiaobo, Wang, Zhaoqing, Chen, Ling-Hao, Liu, Jiale, Wu, Qingyun, Liu, Tongliang
In-context learning is a promising paradigm that utilizes in-context examples as prompts for the predictions of large language models. These prompts are crucial for achieving strong performance. However, since the prompts need to be sampled from a la
Externí odkaz:
http://arxiv.org/abs/2310.10873
Publikováno v:
Zhejiang dianli, Vol 43, Iss 11, Pp 65-73 (2024)
Under the same conditions， the ground capacitance of high-voltage AC submarine cables is over 20 times greater than that of overhead lines， making resonance phenomena more likely during no-load closing of submarine cables. This paper addresses an
Externí odkaz:
https://doaj.org/article/ee3193d838b54f15abd5ee502f8cfeeb
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-14 (2024)
Abstract Rural solid waste (RSW) exhibits distinct characteristics compared to municipal solid waste (MSW), such as dispersed distribution, long governance chains, and low recycling value, making it unsuitable to apply the same management measures as
Externí odkaz:
https://doaj.org/article/315fb8cb9a624617ba536427ffc05199
Autor:
Jin, Xin, Xiao, Jia-Wen, Han, Ling-Hao, Guo, Chunle, Liu, Xialei, Li, Chongyi, Cheng, Ming-Ming
Explicit calibration-based methods have dominated RAW image denoising under extremely low-light environments. However, these methods are impeded by several critical limitations: a) the explicit calibration process is both labor- and time-intensive, b
Externí odkaz:
http://arxiv.org/abs/2308.03448