A layered bidirectional time-surface representation plus a local-flow feature extractor reduces dense trajectory end-point error by 49% on the MultiFlow event-camera benchmark.
Haste: multi-hypothesis asynchronous speeded-up tracking of events
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Labits: Layered Bidirectional Time Surfaces Representation for Event Camera-based Continuous Dense Trajectory Estimation
A layered bidirectional time-surface representation plus a local-flow feature extractor reduces dense trajectory end-point error by 49% on the MultiFlow event-camera benchmark.