Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Zheng, Ping"'
Two-stream graph convolutional neural network fusion for weakly supervised temporal action detection
Publikováno v:
Signal, Image and Video Processing. 16:947-954
Weakly supervised temporal action detection is an important and challenging task, which is to detect temporal intervals of actions and identify category with only video-level labels. Correctly identifying the transition state between action and backg
Publikováno v:
Signal, Image and Video Processing. 15:1663-1670
The performance of crowd counting based on density estimation has been greatly improved with the development of deep learning. However, it is still a major issue to obtain high-quality density map due to the clutter of background, as well as the inte
Real world datasets often contain noisy labels, and learning from such datasets using standard classification approaches may not produce the desired performance. In this paper, we propose a Gaussian Mixture Discriminant Analysis (GMDA) with noisy lab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53b54cddc1621831e48a784b8baab657
Publikováno v:
Signal, Image and Video Processing. 14:437-444
Recent research has shown that the deep subspace learning (DSL) method can extract high-level features and better represent abstract semantics of data for facial expression recognition. While significant advances have been made in this area, traditio
Publikováno v:
Journal of Electronic Imaging. 29
Crowd density estimation is an important part of intelligent crowd monitoring. However, there are still many problems in density estimation due to the complexity of crowd scenes. Aiming at the high-density scenes with varied scales, we present a meth
Publikováno v:
KSII Transactions on Internet and Information Systems. 14
Publikováno v:
Signal, Image and Video Processing. 12:925-932
Most recent researches have demonstrated the effectiveness of using kernel function into sparse representation and collaborative representation, which can overcome the problem of ignoring the nonlinear relationship of samples in face recognition and
Publikováno v:
Signal, Image and Video Processing. 12:835-843
Automatic facial expression recognition has received considerable attention in the research areas of computer vision and pattern recognition. To achieve satisfactory accuracy, deriving a robust facial expression representation is especially important
Publikováno v:
Multimedia Tools and Applications. 77:16947-16963
The performance of facial expression recognition (FER) would be degraded due to the influenced factors such as individual differences and limited number of training samples. Therefore, reducing the influenced factors in facial images may be useful fo
Publikováno v:
IET Computer Vision. 11:675-682
Recently, researchers have proposed different feature descriptors to achieve robust performance for facial expression recognition (FER). However, finding a discriminative feature descriptor remains one of the critical tasks. In this paper, we propose