PolySmart @ TRECVid 2024 视频描述生成（VTT）
PolySmart @ TRECVid 2024 Video Captioning (VTT)
AI总结：
本文针对TRECVid 2024 VTT任务，通过在VTT数据集上微调LLaVA等视觉语言模型，显著提升了视频描述的准确性与领域一致性，实验证明微调模型在多项指标上优于基线。
摘要：
本文介绍了我们在TRECVid 2024的Video-To-Text（VTT）任务中的方法和结果，探索了LLaVA和LLaVA-NeXT-Video等Vision-Language Models（VLMs）为视频内容生成自然语言描述的能力。我们研究了在VTT数据集上微调VLMs的影响，以提升描述准确性、上下文相关性和语言一致性。分析表明，微调显著提升了模型生成更详细且符合领域特征文本的能力，弥合了通用VLM任务与VTT特定需求之间的差距。实验结果表明，我们的微调模型在各项评估指标上均优于基线VLMs，凸显了针对复杂VTT任务进行领域特定微调的重要性。
英文摘要：
In this paper, we present our methods and results for the Video-To-Text (VTT) task at TRECVid 2024, exploring the capabilities of Vision-Language Models (VLMs) like LLaVA and LLaVA-NeXT-Video in generating natural language descriptions for video content. We investigate the impact of fine-tuning VLMs on VTT datasets to enhance description accuracy, contextual relevance, and linguistic consistency. Our analysis reveals that fine-tuning substantially improves the model's ability to produce more detailed and domain-aligned text, bridging the gap between generic VLM tasks and the specialized needs of VTT. Experimental results demonstrate that our fine-tuned model outperforms baseline VLMs across various evaluation metrics, underscoring the importance of domain-specific tuning for complex VTT tasks.
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。
