The authors propose the CRMOT task, the CRTrack benchmark of 13 scenes and 221 language descriptions, and the CRTracker method, which combines CrossMOT-style tracking with APTM text-image matching.
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
-
Cross-View Referring Multi-Object Tracking
The authors propose the CRMOT task, the CRTrack benchmark of 13 scenes and 221 language descriptions, and the CRTracker method, which combines CrossMOT-style tracking with APTM text-image matching.