Siameft: adaptive-time feature extraction hybrid network for rgbe multi-domain object tracking

HIGHLIGHTS

• What: The authors propose the SiamEFT (Siamese Event Frame Tracker), designed to improve the accuracy and efficiency of tracking fast-moving objects in complex scenes. The authors propose a Siamese-based multi-domain feature extraction hybrid network SiamEFT, which employs the cross-network fusion module (CNF) to effectively merge spatio-temporal information from both the frame and event domains.. The adaptivetime attention module (ATA) is designed to extract pertinent information and eliminate redundant information from event frames and the primary objective is to estimate the weight score of each frame within the T event frames. The authors . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.