arXiv:2410.12109cs.CLcs.CV2024-10被引 4

提出新模型OMCAT与数据集OCTAV,提升多模态时间理解能力

OMCAT: Omni Context Aware Transformer

  • 用RoTE改进时间嵌入,增强跨模态时序对齐
  • 在AVQA和OCTAV上达当前最佳性能,提升显著
  • 适合研究多模态时序推理或视频理解的学者

大语言模型在文本生成与理解方面取得显著进展,近期扩展至融合视觉与音频输入的多模态模型。然而,这些模型在细粒度跨模态时间理解方面仍存在困难,尤其在对齐音频与视频流中的事件变化时表现不足。本文提出两个关键贡献:一个新数据集OCTAV(Omni Context and Temporal Audio Video)和一个新模型OMCAT(Omni Context Aware Transformer)。OCTAV旨在捕捉音频与视频中事件的跨模态时序转换。OMCAT采用RoTE(Rotary Time Embeddings),即对RoPE的创新扩展,以增强时间锚定任务中的时序定位能力和计算效率。通过特征对齐、指令微调和OCTAV专项训练的三阶段训练流程,OMCAT在跨模态时间理解方面表现出色。实验验证其在音频-视觉问答(AVQA)任务和OCTAV基准测试中均达到当前最优性能,显著提升了时序推理与跨模态对齐能力。相关数据集与代码将公开,演示页面链接为 https://om-cat.github.io。

原文摘要 · Abstract (English)

Large Language Models (LLMs) have made significant strides in text generation and comprehension, with recent advancements extending into multimodal LLMs that integrate visual and audio inputs. However, these models continue to struggle with fine-grained, cross-modal temporal understanding, particularly when correlating events across audio and video streams. We address these challenges with two key contributions: a new dataset and model, called OCTAV and OMCAT respectively. OCTAV (Omni Context and Temporal Audio Video) is a novel dataset designed to capture event transitions across audio and video. Second, OMCAT (Omni Context Aware Transformer) is a powerful model that leverages RoTE (Rotary Time Embeddings), an innovative extension of RoPE, to enhance temporal grounding and computational efficiency in time-anchored tasks. Through a robust three-stage training pipeline-feature alignment, instruction tuning, and OCTAV-specific training-OMCAT excels in cross-modal temporal understanding. Our model demonstrates state-of-the-art performance on Audio-Visual Question Answering (AVQA) tasks and the OCTAV benchmark, showcasing significant gains in temporal reasoning and cross-modal alignment, as validated through comprehensive experiments and ablation studies. Our dataset and code will be made publicly available. The link to our demo page is https://om-cat.github.io.

多模态时序理解视频问答Transformer

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。