ViQAgent：基于开放词汇接地验证的智能体零样本视频问答
ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation
AI总结：
提出ViQAgent，一种结合思维链与YOLO-World的LLM智能体，用于零样本视频问答，通过开放词汇接地验证增强对象跟踪与对齐，在多个基准上达到最先进性能。
摘要：
视频问答（VideoQA）领域的最新进展引入了基于LLM的智能体、模块化框架和程序化解决方案，取得了令人瞩目的成果。这些系统利用动态智能体和基于记忆的机制来分解复杂任务并优化答案。然而，随着新模型在对象跟踪和推理方面的能力不断提升，在基于时间跨度的对象接地跟踪以及基于推理的决策制定方面仍有显著改进空间，以更好地将对象引用与语言模型输出对齐。本工作提出了一种用于零样本视频问答（VideoQA）的LLM大脑智能体，它将思维链框架与接地推理相结合，并借助YOLO-World来增强对象跟踪和对齐。该方法在视频问答和视频理解领域确立了新的最先进水平，在NExT-QA、iVQA和ActivityNet-QA基准上展现出增强的性能。我们的框架还支持接地时间段的交叉检查，提高了准确性，并为跨多个视频域的验证和输出可靠性提升提供了宝贵支持。代码可在https://github.com/t-montes/viqagent获取。
英文摘要：
Recent advancements in Video Question Answering (VideoQA) have introduced LLM-based agents, modular frameworks, and procedural solutions, yielding promising results. These systems use dynamic agents and memory-based mechanisms to break down complex tasks and refine answers. However, significant improvements remain in tracking objects for grounding over time and decision-making based on reasoning to better align object references with language model outputs, as newer models get better at both tasks. This work presents an LLM-brained agent for zero-shot Video Question Answering (VideoQA) that combines a Chain-of-Thought framework with grounding reasoning alongside YOLO-World to enhance object tracking and alignment. This approach establishes a new state-of-the-art in VideoQA and Video Understanding, showing enhanced performance on NExT-QA, iVQA, and ActivityNet-QA benchmarks. Our framework also enables cross-checking of grounding timeframes, improving accuracy and providing valuable support for verification and increased output reliability across multiple video domains. The code is available at https://github.com/t-montes/viqagent.
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。
