AR2-4FV: 为固定视角视频中的长期接地引用而设计的锚点引用与重识别
AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos
AI总结：
AR2-4FV通过锚点库和重入先验提升固定视角视频中长期引用的准确率和效率。
摘要：
在固定视角视频中实现长期语言引导的引用是一项挑战：被引用的对象可能被遮挡或长时间离开场景后再次出现，而逐帧引用流程在重识别（ReID）不可靠时会漂移。AR2-4FV利用背景稳定性实现长期引用。一个离线的锚点库从静态背景结构中提取；在推理过程中，文本查询与该库对齐以生成锚点图，当被引用对象不存在时，该图充当持久的语义记忆。基于锚点的重入先验加速重捕获，而轻量级的ReID-门控机制利用锚点帧中的位移线索维持身份连续性。该系统在不假设目标在第一帧可见或显式建模外观变化的情况下，预测每帧的边界框。AR2-4FV在最佳基线基础上实现了Re-Capture Rate（RCR）提升10.3%和Re-Capture Latency（RCL）减少24.2%，消融研究进一步证实了锚点图、重入先验和ReID-门控机制的优势。
英文摘要：
Long-term language-guided referring in fixed-view videos is challenging: the referent may be occluded or leave the scene for long intervals and later re-enter, while framewise referring pipelines drift as re-identification (ReID) becomes unreliable. AR2-4FV leverages background stability for long-term referring. An offline Anchor Bank is distilled from static background structures; at inference, the text query is aligned with this bank to produce an Anchor Map that serves as persistent semantic memory when the referent is absent. An anchor-based re-entry prior accelerates re-capture upon return, and a lightweight ReID-Gating mechanism maintains identity continuity using displacement cues in the anchor frame. The system predicts per-frame bounding boxes without assuming the target is visible in the first frame or explicitly modeling appearance variations. AR2-4FV achieves +10.3% Re-Capture Rate (RCR) improvement and -24.2% Re-Capture Latency (RCL) reduction over the best baseline, and ablation studies further confirm the benefits of the Anchor Map, re-entry prior, and ReID-Gating.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
