MVTD is a 182-sequence, 150,000-frame maritime visual tracking benchmark with four object classes, showing that state-of-the-art trackers degrade on maritime scenes and improve after fine-tuning.
Foundationpose: Unified 6d pose estimation and tracking of novel objects,
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
MVTD: A Benchmark Dataset for Maritime Visual Object Tracking
MVTD is a 182-sequence, 150,000-frame maritime visual tracking benchmark with four object classes, showing that state-of-the-art trackers degrade on maritime scenes and improve after fine-tuning.