Scholarlink

In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual question answering, face computational burdens when processing long videos due to the excessive visual tokens. LLaMA-VID addresses this issue by representing each frame with two distinct tokens, namely context token and content token. The context token encodes the overall image context based on user input, whereas the content token encapsulates visual cues in each frame. This dual-token strategy significantly reduces the overload of long videos while preserving critical information. Generally, LLaMA-VID empowers existing frameworks to support hour-long videos and pushes their upper limit with an extra context token. It is demonstrated to surpass previous methods on most of video- or image-based benchmarks. Code and models are available at  https://github.com/dvlab-research/LLaMA-VID .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Yanwei Li,
  • Chengyao Wang,
  • Jiaya Jia

摘要

In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual question answering, face computational burdens when processing long videos due to the excessive visual tokens. LLaMA-VID addresses this issue by representing each frame with two distinct tokens, namely context token and content token. The context token encodes the overall image context based on user input, whereas the content token encapsulates visual cues in each frame. This dual-token strategy significantly reduces the overload of long videos while preserving critical information. Generally, LLaMA-VID empowers existing frameworks to support hour-long videos and pushes their upper limit with an extra context token. It is demonstrated to surpass previous methods on most of video- or image-based benchmarks. Code and models are available at  https://github.com/dvlab-research/LLaMA-VID .