Zobrazeno 1 - 10
of 3 138
pro vyhledávání: '"Cao, Yun"'
Autor:
Wang, Qilin, Jiang, Zhengkai, Xu, Chengming, Zhang, Jiangning, Wang, Yabiao, Zhang, Xinyi, Cao, Yun, Cao, Weijian, Wang, Chengjie, Fu, Yanwei
Human image animation involves generating a video from a static image by following a specified pose sequence. Current approaches typically adopt a multi-stage pipeline that separately learns appearance and motion, which often leads to appearance degr
Externí odkaz:
http://arxiv.org/abs/2405.18156
Autor:
Cao, Yun-Hao, Wu, Jianxin
Self-supervised learning (SSL) has developed rapidly in recent years. However, most of the mainstream methods are computationally expensive and rely on two (or more) augmentations for each image to construct positive pairs. Moreover, they mainly focu
Externí odkaz:
http://arxiv.org/abs/2404.19289
With the development of deep learning technology, various forgery methods emerge endlessly. Meanwhile, methods to detect these fake videos have also achieved excellent performance on some datasets. However, these methods suffer from poor generalizati
Externí odkaz:
http://arxiv.org/abs/2309.16126
Publikováno v:
Marine Economics and Management, 2023, Vol. 7, Issue 1, pp. 1-17.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/MAEM-08-2023-0007
We propose universally slimmable self-supervised learning (dubbed as US3L) to achieve better accuracy-efficiency trade-offs for deploying self-supervised models across different devices. We observe that direct adaptation of self-supervised learning (
Externí odkaz:
http://arxiv.org/abs/2303.06870
Point cloud completion has become increasingly popular among generation tasks of 3D point clouds, as it is a challenging yet indispensable problem to recover the complete shape of a 3D object from its partial observation. In this paper, we propose a
Externí odkaz:
http://arxiv.org/abs/2207.10315
With the success of self-supervised learning (SSL), it has become a mainstream paradigm to fine-tune from self-supervised pretrained models to boost the performance on downstream tasks. However, we find that current SSL models suffer severe accuracy
Externí odkaz:
http://arxiv.org/abs/2207.05432
Few-shot recognition learns a recognition model with very few (e.g., 1 or 5) images per category, and current few-shot learning methods focus on improving the average accuracy over many episodes. We argue that in real-world applications we may often
Externí odkaz:
http://arxiv.org/abs/2203.06574
Vision Transformers (ViTs) is emerging as an alternative to convolutional neural networks (CNNs) for visual recognition. They achieve competitive results with CNNs but the lack of the typical convolutional inductive bias makes them more data-hungry t
Externí odkaz:
http://arxiv.org/abs/2201.10728
In recent years, the spread of fake videos has brought great influence on individuals and even countries. It is important to provide robust and reliable results for fake videos. The results of conventional detection methods are not reliable and not r
Externí odkaz:
http://arxiv.org/abs/2112.08117