Dynamic Reasoning Routing for Efficient Online Video Object Segmentation

Online reasoning video object segmentation aims to segment targets in an incoming video stream based on complex or implicit language queries. Maintaining accurate target grounding requires timely adaptation to evolving visual evidence. However, existing invocation schedules incur substantial reasoning costs without consistent accuracy gains. To address this, we propose Dynamic Reasoning Routing (DRR), a training-free framework that adaptively schedules semantic reassessment using motion-compensated residuals. By monitoring changes in the target and its context at low cost, DRR reduces redundant reasoning while remaining responsive to evolving visual evidence. To limit error accumulation during propagation, DRR further introduces confidence-weighted mask encoding, which softens masks from low-confidence reassessments. Experiments on five reasoning and referring VOS benchmarks show an improved accuracy–efficiency trade-off. On ReasonVOS, DRR improves accuracy at $6.2$–$7.0\times$ the throughput of matched periodic baselines, and surpasses the prior art by $13.0$ $\mathcal{J}$&$\mathcal{F}$ with a $1.4\times$ speedup. A paired-replay analysis further demonstrates that DRR provides greater average benefit for subsequent segmentation than periodic scheduling. Code will be publicly available.