Zobrazeno 1 - 10
of 1 728
pro vyhledávání: '"Wu, ZhongHua"'
While recent image warping approaches achieved remarkable success on existing benchmarks, they still require training separate models for each specific task and cannot generalize well to different camera models or customized manipulations. To address
Externí odkaz:
http://arxiv.org/abs/2404.10716
Whole-body pose and shape estimation aims to jointly predict different behaviors (e.g., pose, hand gesture, facial expression) of the entire human body from a monocular image. Existing methods often exhibit degraded performance under the complexity o
Externí odkaz:
http://arxiv.org/abs/2312.08730
Makeup transfer is a process of transferring the makeup style from a reference image to the source images, while preserving the source images' identities. This technique is highly desirable and finds many applications. However, existing methods lack
Externí odkaz:
http://arxiv.org/abs/2311.16828
In this work, we tackle the challenging problem of long-tailed image recognition. Previous long-tailed recognition approaches mainly focus on data augmentation or re-balancing strategies for the tail classes to give them more attention during model t
Externí odkaz:
http://arxiv.org/abs/2309.07186
New lesion segmentation is essential to estimate the disease progression and therapeutic effects during multiple sclerosis (MS) clinical treatments. However, the expensive data acquisition and expert annotation restrict the feasibility of applying la
Externí odkaz:
http://arxiv.org/abs/2307.04513
Autor:
Liu, Weide, Wu, Zhonghua, Zhao, Yang, Fang, Yuming, Foo, Chuan-Sheng, Cheng, Jun, Lin, Guosheng
Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes. To overcome this limitation, the task of generalized few-shot semantic segmentation
Externí odkaz:
http://arxiv.org/abs/2303.13724
Autor:
Luo, Zhipeng, Zhang, Gongjie, Zhou, Changqing, Wu, Zhonghua, Tao, Qingyi, Lu, Lewei, Lu, Shijian
The task of 3D single object tracking (SOT) with LiDAR point clouds is crucial for various applications, such as autonomous driving and robotics. However, existing approaches have primarily relied on appearance matching or motion modeling within only
Externí odkaz:
http://arxiv.org/abs/2303.07605
Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used
Externí odkaz:
http://arxiv.org/abs/2303.05164
Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model training.
Externí odkaz:
http://arxiv.org/abs/2207.09084
In this work, we address the challenging task of long-tailed image recognition. Previous long-tailed recognition methods commonly focus on the data augmentation or re-balancing strategy of the tail classes to give more attention to tail classes durin
Externí odkaz:
http://arxiv.org/abs/2206.01010