TenRPCANet uses a Video Swin Transformer with low-rank tensor-inspired tokenization to separate dim moving targets from low-rank video backgrounds, reaching strong benchmark results in infrared and space imagery.
Multilinear supervised neighbor- hood embedding of a local descriptor tensor for scene/object recognition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Motion Cues and Structural Sparsity: Revisiting Small Moving Target Detection
TenRPCANet uses a Video Swin Transformer with low-rank tensor-inspired tokenization to separate dim moving targets from low-rank video backgrounds, reaching strong benchmark results in infrared and space imagery.