Zobrazeno 1 - 10
of 59
pro vyhledávání: '"Yong, Junhai"'
Deep learning methods have achieved excellent performance in pose estimation, but the lack of robustness causes the keypoints to change drastically between similar images. In view of this problem, a stable heatmap regression method is proposed to all
Externí odkaz:
http://arxiv.org/abs/2105.03569
As an important method of handling potential uncertainties in numerical simulations, ensemble simulation has been widely applied in many disciplines. Visualization is a promising and powerful ensemble simulation analysis method. However, conventional
Externí odkaz:
http://arxiv.org/abs/2011.01497
Publikováno v:
Journal of Visualization, 2019, 22(1): 109-124
Fencing is a sport that relies heavily on the use of tactics. However, most existing methods for analyzing fencing data are based on statistical models in which hidden patterns are difficult to discover. Unlike sequential games, such as tennis and ta
Externí odkaz:
http://arxiv.org/abs/2011.01446
We propose a simple and highly query-efficient black-box adversarial attack named SWITCH, which has a state-of-the-art performance in the score-based setting. SWITCH features a highly efficient and effective utilization of the gradient of a surrogate
Externí odkaz:
http://arxiv.org/abs/2009.07191
There is an urgent need for an effective video classification method by means of a small number of samples. The deficiency of samples could be effectively alleviated by generating samples through Generative Adversarial Networks (GAN), but the generat
Externí odkaz:
http://arxiv.org/abs/1909.12929
Insufficient labeled training datasets is one of the bottlenecks of 3D hand pose estimation from monocular RGB images. Synthetic datasets have a large number of images with precise annotations, but the obvious difference with real-world datasets impa
Externí odkaz:
http://arxiv.org/abs/1909.05666
Deep neural networks (DNNs) are vulnerable to adversarial attack which is maliciously implemented by adding human-imperceptible perturbation to images and thus leads to incorrect prediction. Existing studies have proposed various methods to detect th
Externí odkaz:
http://arxiv.org/abs/1908.02199
We propose a real-time DNN-based technique to segment hand and object of interacting motions from depth inputs. Our model is called DenseAttentionSeg, which contains a dense attention mechanism to fuse information in different scales and improves the
Externí odkaz:
http://arxiv.org/abs/1903.12368
Publikováno v:
Neurocomputing 355 (2019) 35-47
Detecting action units (AUs) on human faces is challenging because various AUs make subtle facial appearance change over various regions at different scales. Current works have attempted to recognize AUs by emphasizing important regions. However, the
Externí odkaz:
http://arxiv.org/abs/1812.05788
Publikováno v:
In Neurocomputing 1 July 2022 492:322-342
