TAR：基于时间锚的视频时间定位推理
TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding
AI总结：
TAR通过引入时间锚机制，提升视频时间定位任务中推理过程的可信度和自主性，采用自举方法生成高质量推理轨迹，实现更精确的最终预测。
摘要：
视频时间定位（VTG）旨在定位与自然语言查询对应的视频片段。尽管近期的大型视觉-语言模型（LVLMs）利用强化学习生成思维链（CoT），但通常仅依赖结果监督，导致推理过程与视觉内容脱节，产生幻觉。现有方法通过外部监督或独立奖励模型缓解问题，但计算成本高且易产生僵化模式。为此，我们提出TAR（时间锚约束推理）框架，引入时间锚（T-anchor）作为透明且可审计的检查点机制。T-anchor强制在CoT中进行逐步细化，迫使模型持续将中间思考 grounded 在视觉证据中，并迭代校准时间预测，从而显著提升推理过程的可信度和自主性及最终准确性。此外，我们引入自举范式，仅使用标准7B模型自动获取高质量CoT数据，消除对超大规模模型的依赖。大量实验表明，TAR在性能上达到最先进的水平，并生成忠实、自主且逐步细化的推理轨迹。
英文摘要：
Video Temporal Grounding (VTG) aims to localize specific video segments corresponding to natural language queries. While recent Large Vision-Language Models (LVLMs) employ Reinforcement Learning to generate Chains-of-Thought (CoT), they typically rely solely on outcome-based supervision. Consequently, this often leads to hallucinations, where the reasoning process becomes disconnected from the visual content and the final prediction. Existing attempts to mitigate this by relying on external supervision from larger models or separate reward models are computationally expensive and prone to rigid patterns. To address these challenges, we propose TAR (Temporal Anchor-Constrained Reasoning), a framework that introduces the temporal anchor (T-anchor) as a transparent and auditable checkpoint mechanism. T-anchor enforces progressive refinement within the CoT, compelling the model to continuously ground its intermediate thoughts in visual evidence and iteratively calibrate temporal predictions, thereby significantly enhancing the faithfulness and autonomy of the reasoning process and final accuracy. Furthermore, we introduce a bootstrapping paradigm that automatically harvests high-quality CoT data using only a standard 7B model, eliminating the dependency on ultra-large models. Extensive experiments demonstrate that TAR achieves state-of-the-art performance and generates faithful, autonomous, and progressively refined reasoning traces.
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。
