Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Mao, Yunyao"'
We introduce MotionRL, the first approach to utilize Multi-Reward Reinforcement Learning (RL) for optimizing text-to-motion generation tasks and aligning them with human preferences. Previous works focused on improving numerical performance metrics o
Externí odkaz:
http://arxiv.org/abs/2410.06513
Autor:
Zhu, Defa, Huang, Hongzhi, Huang, Zihao, Zeng, Yutao, Mao, Yunyao, Wu, Banggu, Min, Qiyang, Zhou, Xun
We present hyper-connections, a simple yet effective method that can serve as an alternative to residual connections. This approach specifically addresses common drawbacks observed in residual connection variants, such as the seesaw effect between gr
Externí odkaz:
http://arxiv.org/abs/2409.19606
Sign language recognition (SLR) has long been plagued by insufficient model representation capabilities. Although current pre-training approaches have alleviated this dilemma to some extent and yielded promising performance by employing various prete
Externí odkaz:
http://arxiv.org/abs/2405.20666
Text-driven human motion generation, as one of the vital tasks in computer-aided content creation, has recently attracted increasing attention. While pioneering research has largely focused on improving numerical performance metrics on given datasets
Externí odkaz:
http://arxiv.org/abs/2405.15541
Recent progresses on self-supervised 3D human action representation learning are largely attributed to contrastive learning. However, in conventional contrastive frameworks, the rich complementarity between different skeleton modalities remains under
Externí odkaz:
http://arxiv.org/abs/2310.15568
In 3D human action recognition, limited supervised data makes it challenging to fully tap into the modeling potential of powerful networks such as transformers. As a result, researchers have been actively investigating effective self-supervised pre-t
Externí odkaz:
http://arxiv.org/abs/2308.07092
Segment anything model (SAM) has achieved great success in the field of natural image segmentation. Nevertheless, SAM tends to consider shadows as background and therefore does not perform segmentation on them. In this paper, we propose ShadowSAM, a
Externí odkaz:
http://arxiv.org/abs/2305.16698
In 3D action recognition, there exists rich complementary information between skeleton modalities. Nevertheless, how to model and utilize this information remains a challenging problem for self-supervised 3D action representation learning. In this wo
Externí odkaz:
http://arxiv.org/abs/2208.12448
Semi-supervised video object segmentation is a task of segmenting the target object in a video sequence given only a mask annotation in the first frame. The limited information available makes it an extremely challenging task. Most previous best-perf
Externí odkaz:
http://arxiv.org/abs/2108.03679
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.