Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Fu, Zehua"'
Bird's-Eye-View (BEV) representation has emerged as a mainstream paradigm for multi-view 3D object detection, demonstrating impressive perceptual capabilities. However, existing methods overlook the geometric quality of BEV representation, leaving it
Externí odkaz:
http://arxiv.org/abs/2409.01816
Recent attention has been devoted to the pursuit of learning semantic segmentation models exclusively from image tags, a paradigm known as image-level Weakly Supervised Semantic Segmentation (WSSS). Existing attempts adopt the Class Activation Maps (
Externí odkaz:
http://arxiv.org/abs/2408.02039
Human pose estimation and tracking are fundamental tasks for understanding human behaviors in videos. Existing top-down framework-based methods usually perform three-stage tasks: human detection, pose estimation and tracking. Although promising resul
Externí odkaz:
http://arxiv.org/abs/2310.18920
Tracking multiple athletes in sports videos is a very challenging Multi-Object Tracking (MOT) task, since athletes often have the same appearance and are intimately covered with each other, making a common occlusion problem becomes an abhorrent dupli
Externí odkaz:
http://arxiv.org/abs/2209.12248
Autor:
Du, Ye, Shen, Yujun, Wang, Haochen, Fei, Jingjing, Li, Wei, Wu, Liwei, Zhao, Rui, Fu, Zehua, Liu, Qingjie
Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and in turn teach itself. To obtain valid supervision, active attempts typ
Externí odkaz:
http://arxiv.org/abs/2209.06993
Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers. However, self-at
Externí odkaz:
http://arxiv.org/abs/2205.03776
Occlusions are very common in face images in the wild, leading to the degraded performance of face-related tasks. Although much effort has been devoted to removing occlusions from face images, the varying shapes and textures of occlusions still chall
Externí odkaz:
http://arxiv.org/abs/2112.08022
Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap between classification and segmentation still hampers the model to generate
Externí odkaz:
http://arxiv.org/abs/2110.07110
Although much progress has been made recently in 3D face reconstruction, most previous work has been devoted to predicting accurate and fine-grained 3D shapes. In contrast, relatively little work has focused on generating high-fidelity face textures.
Externí odkaz:
http://arxiv.org/abs/2106.08148
Publikováno v:
IJCB,2020,pp. 1-10
The existing auto-encoder based face pose editing methods primarily focus on modeling the identity preserving ability during pose synthesis, but are less able to preserve the image style properly, which refers to the color, brightness, saturation, et
Externí odkaz:
http://arxiv.org/abs/2106.07310