arXiv cs.AI· Chaohong Guo, Xun Mo, Yongwei Nie, Fei Ma, Xuemiao Xu, Chengjiang Long·· 4 小时前AI 评分24
TAR:用时间锚点约束推理,提升视频时序定位的忠实度
TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding
AI 导读
TAR 提出时间锚点(T-anchor)作为可审计的检查点机制,强制 LVLM 在 Chain-of-Thought 中持续将中间推理锚定到视觉证据并迭代校准时序预测,减少推理与视频内容脱节的幻觉。该方法还引入仅用标准 7B 模型自动采集高质量 CoT 数据的自举范式,摆脱对超大模型的依赖,实验达到 SOTA 并生成忠实、自主、逐步细化的推理轨迹,已被 ECCV2026 接收。
正文 · 原文
Abstract: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.
| Comments: | Accepted by ECCV2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2508.07683 [cs.CV] |
| (or arXiv:2508.07683v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2508.07683 arXiv-issued DOI via DataCite |
Submission history
From: Chaohong Guo [view email]
[v1]
Mon, 11 Aug 2025 06:59:32 UTC (2,172 KB)
[v2]
Mon, 29 Jun 2026 02:15:03 UTC (1,192 KB)
[v3]
Tue, 17 Nov 2026 07:55:57 UTC (1,196 KB)
来源:arXiv cs.AI · arxiv.org