MCITrack uses Mamba hidden states and per-block cross-attention to pass video-level context through a transformer tracker, reaching 76.6% AUC on LaSOT and 80.0% AO on GOT-10k.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring Enhanced Contextual Information for Video-Level Object Tracking
MCITrack uses Mamba hidden states and per-block cross-attention to pass video-level context through a transformer tracker, reaching 76.6% AUC on LaSOT and 80.0% AO on GOT-10k.