Introduces a joint optimization framework coupling deep spectral unmixing with target localization via material prompts and a weighted unmixing loss for hyperspectral object tracking.
Autoregressive queries for adaptive tracking with spatio-temporal trans- formers,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A three-stage ViT with sparsity-aware MoE and adaptive inference depth delivers improved accuracy-efficiency trade-off for event-stream visual tracking on FE240hz, COESOT, and EventVOT benchmarks.
citing papers explorer
-
End-to-End Unmixing with Material Prompts for Hyperspectral Object Tracking
Introduces a joint optimization framework coupling deep spectral unmixing with target localization via material prompts and a weighted unmixing loss for hyperspectral object tracking.
-
Dynamic Pondering Sparsity-aware Mixture-of-Experts Transformer for Event Stream based Visual Object Tracking
A three-stage ViT with sparsity-aware MoE and adaptive inference depth delivers improved accuracy-efficiency trade-off for event-stream visual tracking on FE240hz, COESOT, and EventVOT benchmarks.