Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Xiaolin Ma"'
Publikováno v:
2019 11th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA).
Scene text detection methods based on direct regression are always efficient and accuracy. However, the previous methods also have obvious shortcomings. The central text pixels always constrained the text box in the process of direct regression, whic
Publikováno v:
2019 11th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA).
Human face is the most important content to distinguish and remember individuals from different characters. The rich information contained in it allows people to perform information transmission and identity authentication through face images. Compar
Publikováno v:
2019 11th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA).
The rapid development of deep learning in recent years has led to breakthroughs in more and more problems, such as image recognition and object detection. Human-object interaction(HOI) detection is an important issue in image comprehension, which has
Publikováno v:
2019 11th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA).
Deep learning is increasingly used in target tracking, due to the CNN's powerful feature learning capabilities. Speed and accuracy are important for specific target tracking. Target tracking based on the Siamese network is potential in these two aspe
Publikováno v:
2019 11th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA).
Facial expression synthesis has always been a research hotspot in the field of computer vision and graphics. The facial expressions are complex and vary from person to person. It is a challenging task to synthesize a rich and diverse facial expressio
Publikováno v:
2019 11th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA).
Deep convolutional networks have made progress in many tasks in vision, such as image classification, target detection, target segmentation, etc., two-stream ConvNets, C2D+LSTM method and 3DCNN method, successfully introduces the advantages of convol