Diff-MM reuses a pre-trained Stable Diffusion UNet as a tracking feature extractor and obtains state-of-the-art results across RGB-N/D/T/E tracking benchmarks with a single set of parameters.
ECO: Efficient convolution operators for tracking
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
unclear 1representative citing papers
citing papers explorer
-
Diff-MM: Exploring Pre-trained Text-to-Image Generation Model for Unified Multi-modal Object Tracking
Diff-MM reuses a pre-trained Stable Diffusion UNet as a tracking feature extractor and obtains state-of-the-art results across RGB-N/D/T/E tracking benchmarks with a single set of parameters.