TimeExpert：一种专家引导的视频大语言模型用于视频时间定位
TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding
AI总结：
TimeExpert提出基于混合专家的视频大语言模型，通过动态路由任务特定令牌到专门专家，有效分解视频时间定位任务，在密集视频字幕、时刻检索和高光检测等任务上达到最先进性能。
摘要：
视频时间定位（VTG）旨在根据文本查询精确识别视频事件片段。VTG任务的输出表现为事件序列，每个事件由精确的时间戳、显著性分数和文本描述定义。尽管近期取得了进展，现有视频大语言模型（Video-LLMs）仍存在一个根本性局限：它们通过相同且静态的路径处理所有任务令牌，未能认识到时间定位、显著性评估和文本生成是根本不同的任务，需要专门处理。为解决这一问题，我们提出了TimeExpert，一种基于混合专家（MoE）的视频大语言模型，通过将任务特定令牌（如时间戳、显著性分数）动态路由到专门专家，有效分解VTG任务，并提高了计算效率。我们的设计选择使得每个子任务都能得到精确处理，从而在多种VTG应用中改进了事件建模。大量实验表明，TimeExpert在密集视频字幕、时刻检索和视频高光检测等各类VTG任务上持续实现了最先进的性能。
英文摘要：
Video Temporal Grounding (VTG) aims to precisely identify video event segments in response to textual queries. The outputs of VTG tasks manifest as sequences of events, each defined by precise timestamps, saliency scores, and textual descriptions. Despite recent advances, a fundamental limitation persists in existing Video Large Language Models (Video-LLMs): they process all task tokens through identical and static pathways, failing to recognize that temporal localization, saliency assessment, and textual generation represent fundamentally distinct tasks requiring specialized processing. To address this, we introduce TimeExpert, a Mixture-of-Experts (MoE)-based Video-LLM that effectively decomposes VTG tasks by dynamically routing task-specific tokens (e.g., timestamps, saliency scores) to specialized experts, with increased computational efficiency. Our design choices enable precise handling of each subtask, leading to improved event modeling across diverse VTG applications. Extensive experiments demonstrate that TimeExpert consistently achieves state-of-the-art performance on various VTG tasks such as Dense Video Captioning, Moment Retrieval, and Video Highlight Detection.
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。
