articleIEEE Transactions on Image ProcessingJan 1, 2025HYBRID OA

Motion and Appearance Decoupling Representation for Event Cameras

NCNuo ChenBLBoyang LiYWYingqian WangXYXinyi YingLWLongguang Wang

National University of Defense Technology · PLA Air Force Aviation University · +1 more institution

PubMed
Indexed incrossrefpubmed

Abstract

Event cameras, with high temporal resolution and high dynamic range, have shown great potential under extreme scenarios such as high-speed movement and low illumination. However, previous event representation methods typically aggregate event data into a single dense tensor, often overlooking the dynamic changes of events within a given time unit. This limitation can introduce historical artifacts and semantic inconsistencies, ultimately degrading model performance. Inspired by human visual prior, we propose a motion and appearance decoupling (MAD) event representation to disentangle the mixed spatial-temporal event tensor into two independent branches. This bio-inspired design helps the network extract…

Citation impact

49
total citations
FWCI
60.43
Percentile
100%
References
65
Citations per year

Authors

9

Topics & keywords

Topics
Keywords
  • Discriminative model
  • Event (particle physics)
  • Representation (politics)
  • Decoupling (probability)
  • Pattern recognition (psychology)
  • Feature extraction
  • Pyramid (geometry)
  • Feature (linguistics)
No related works found for this paper.

Funding