SENTRY is a plug-and-play module that replaces confidence-based memory writes with neighbor-aware cycle-consistent validation in SAM2 trackers, yielding new zero-shot SOTA results on LaSOT, GOT-10k and other benchmarks.
hub
Title resolution pending
3 Pith papers cite this work, alongside 3,984 external citations. Polarity classification is still indexing.
3
Pith papers citing it
3,984
external citations · OpenAlex
hub tools
years
2026 3representative citing papers
Continual learning robots form a significantly more stable invariant subnetwork than constant-task controls, and preserving it improves adaptation while damaging it hurts performance.
Iterative Best Response achieves competitive task completion rates with lower computation time than baselines in simulated multi-drone delivery under uncertainty and sparse communication.
citing papers explorer
-
SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Tracking
SENTRY is a plug-and-play module that replaces confidence-based memory writes with neighbor-aware cycle-consistent validation in SAM2 trackers, yielding new zero-shot SOTA results on LaSOT, GOT-10k and other benchmarks.
-
Evidence of an Emergent "Self" in Continual Robot Learning
Continual learning robots form a significantly more stable invariant subnetwork than constant-task controls, and preserving it improves adaptation while damaging it hurts performance.
-
Dynamic Multi-Robot Task Allocation under Uncertainty and Communication Constraints: A Game-Theoretic Approach
Iterative Best Response achieves competitive task completion rates with lower computation time than baselines in simulated multi-drone delivery under uncertainty and sparse communication.