ETCTrack compresses template tokens by 60% in visual trackers via an adaptive compressor and hierarchical interaction, cutting MACs 21.4% with 0.4% accuracy drop on seven benchmarks.
Masked autoencoders are scalable vision learners
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
The inaugural Controllable Bokeh Rendering Challenge at NTIRE 2026 received 8 valid submissions, mostly refinements of the Bokehlicious baseline, evaluated on unseen portrait images via fidelity metrics and expert perceptual assessment.
citing papers explorer
-
An Efficient Token Compression Framework for Visual Object Tracking
ETCTrack compresses template tokens by 60% in visual trackers via an adaptive compressor and hierarchical interaction, cutting MACs 21.4% with 0.4% accuracy drop on seven benchmarks.
-
The First Controllable Bokeh Rendering Challenge at NTIRE 2026
The inaugural Controllable Bokeh Rendering Challenge at NTIRE 2026 received 8 valid submissions, mostly refinements of the Bokehlicious baseline, evaluated on unseen portrait images via fidelity metrics and expert perceptual assessment.