ACTrack coordinates a tracker, a segmentation model, and a VLM through event-triggered conflicts, reporting state-of-the-art RGB and multimodal tracking with 30% trainable parameters.
In: 7th International Conference on Learning Representations, ICLR (2019)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Models as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Tracking
ACTrack coordinates a tracker, a segmentation model, and a VLM through event-triggered conflicts, reporting state-of-the-art RGB and multimodal tracking with 30% trainable parameters.