UniversalVTG: 一种通用且轻量的视频时间定位基础模型
UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding
AI总结：
本文提出UniversalVTG，一种通用轻量视频时间定位模型，通过大规模跨数据集预训练实现高效长视频定位，优于专用模型且比大语言模型更轻量。
摘要：
视频时间定位（VTG）通常使用领域特定模型，但跨领域和查询风格转移效果差。近期尝试用大多模态语言模型（MLLMs）改进，但计算成本高且视频上下文有限。本文提出UniversalVTG，通过统一监督保持模型轻量。该模型通过离线查询统一器将异构查询格式转换为共享声明性空间，减少语言不匹配并防止朴素联合训练中的负迁移。结合高效定位头，UniversalVTG可处理长无剪辑视频。在多个基准测试中，一个UniversalVTG检查点在性能上优于专用VTG模型。此外，尽管比近期基于MLLM的方法小100倍以上，UniversalVTG在多个基准测试中达到或超过其准确性，提供了一种实用的替代方案，无需依赖参数密集的MLLMs。
英文摘要：
Video temporal grounding (VTG) is typically tackled with dataset-specific models that transfer poorly across domains and query styles. Recent efforts to overcome this limitation have adapted large multimodal language models (MLLMs) to VTG, but their high compute cost and limited video context still hinder long-video grounding. We instead scale unified supervision while keeping the model lightweight. We present UniversalVTG, a single VTG model trained with large-scale cross-dataset pretraining. An offline Query Unifier canonicalizes heterogeneous query formats into a shared declarative space, reducing linguistic mismatch and preventing the negative transfer observed under naïve joint training. Combined with an efficient grounding head, UniversalVTG scales to long, untrimmed videos. Across diverse benchmarks-GoalStep-StepGrounding, Ego4D-NLQ, TACoS, Charades-STA, and ActivityNet-Captions-one UniversalVTG checkpoint achieves state-of-the-art performance versus dedicated VTG models. Moreover, despite being $>100\times$ smaller than recent MLLM-based approaches, UniversalVTG matches or exceeds their accuracy on multiple benchmarks, offering a practical alternative to parameter-heavy MLLMs.
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。
