Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Fikriansyah Adzaka"'
Publikováno v:
ICT Express, Vol 9, Iss 2, Pp 258-263 (2023)
Combining multiple models is a well-known technique to improve predictive performance in challenging tasks such as object detection in UAV imagery. In this paper, we propose fusion of transformer-based and convolutional neural network-based (CNN) mod
Externí odkaz:
https://doaj.org/article/cad0d68d54f04c5aa8e14fbb11d82af5
Publikováno v:
Journal of King Saud University: Computer and Information Sciences, Vol 35, Iss 4, Pp 50-62 (2023)
Many existing video captioning methods capture action information in the video by exploiting features extracted from an action recognition model. However, directly using the action features without object-specific representation may not well capture
Externí odkaz:
https://doaj.org/article/4439d9b584ad4ea5940dcfa5449c6003