Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Jiang, Boyuan"'
Autor:
Li, Bang, Luo, Donghao, Liang, Yujie, Yang, Jing, Ding, Zengmao, Peng, Xu, Jiang, Boyuan, Han, Shengwei, Sui, Dan, Qin, Peichao, Wu, Pian, Wang, Chaoyang, Qi, Yun, Jin, Taisong, Wang, Chengjie, Huang, Xiaoming, Shu, Zhan, Ji, Rongrong, Liu, Yongge, Wu, Yunsheng
Oracle bone inscriptions(OBI) is the earliest developed writing system in China, bearing invaluable written exemplifications of early Shang history and paleography. However, the task of deciphering OBI, in the current climate of the scholarship, can
Externí odkaz:
http://arxiv.org/abs/2407.03900
Autor:
Wu, Kai, Jiang, Boyuan, Jiang, Zhengkai, He, Qingdong, Luo, Donghao, Wang, Shengzhi, Liu, Qingwen, Wang, Chengjie
Multimodal large language models (MLLMs) contribute a powerful mechanism to understanding visual information building on large language models. However, MLLMs are notorious for suffering from hallucinations, especially when generating lengthy, detail
Externí odkaz:
http://arxiv.org/abs/2405.20081
Autor:
Wang, Mengmeng, Xing, Jiazheng, Jiang, Boyuan, Chen, Jun, Mei, Jianbiao, Zuo, Xingxing, Dai, Guang, Wang, Jingdong, Liu, Yong
Publikováno v:
AAAI2024
Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevertheless, prevailing approaches
Externí odkaz:
http://arxiv.org/abs/2401.11649
Autor:
Peng, Xu, Zhu, Junwei, Jiang, Boyuan, Tai, Ying, Luo, Donghao, Zhang, Jiangning, Lin, Wei, Jin, Taisong, Wang, Chengjie, Ji, Rongrong
Recent advancements in personalized image generation using diffusion models have been noteworthy. However, existing methods suffer from inefficiencies due to the requirement for subject-specific fine-tuning. This computationally intensive process hin
Externí odkaz:
http://arxiv.org/abs/2312.06354
3D human pose estimation has been a long-standing challenge in computer vision and graphics, where multi-view methods have significantly progressed but are limited by the tedious calibration processes. Existing multi-view methods are restricted to fi
Externí odkaz:
http://arxiv.org/abs/2309.04756
Autor:
Kong, Lingtong, Jiang, Boyuan, Luo, Donghao, Chu, Wenqing, Tai, Ying, Wang, Chengjie, Yang, Jie
Video frame interpolation is an important low-level vision task, which can increase frame rate for more fluent visual experience. Existing methods have achieved great success by employing advanced motion models and synthesis networks. However, the sp
Externí odkaz:
http://arxiv.org/abs/2309.03508
Motion retargeting is a fundamental problem in computer graphics and computer vision. Existing approaches usually have many strict requirements, such as the source-target skeletons needing to have the same number of joints or share the same topology.
Externí odkaz:
http://arxiv.org/abs/2306.08006
Autor:
Kong, Lingtong, Jiang, Boyuan, Luo, Donghao, Chu, Wenqing, Huang, Xiaoming, Tai, Ying, Wang, Chengjie, Yang, Jie
Prevailing video frame interpolation algorithms, that generate the intermediate frames from consecutive inputs, typically rely on complex model architectures with heavy parameters or large delay, hindering them from diverse real-time applications. In
Externí odkaz:
http://arxiv.org/abs/2205.14620
Autor:
Wu, Mingyu, Jiang, Boyuan, Luo, Donghao, Yan, Junchi, Wang, Yabiao, Tai, Ying, Wang, Chengjie, Li, Jilin, Huang, Feiyue, Yang, Xiaokang
For action recognition learning, 2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame. Recent efforts attempt to capture motion information by establishing inter-frame connec
Externí odkaz:
http://arxiv.org/abs/2103.12278
In facial action unit (AU) recognition tasks, regional feature learning and AU relation modeling are two effective aspects which are worth exploring. However, the limited representation capacity of regional features makes it difficult for relation mo
Externí odkaz:
http://arxiv.org/abs/2102.12154