Extending image-based Large Multimodal Models (LMM) to videos is challenging due to the inherent complexity of video data. The recent approaches extending image-based LMM to videos either lack the grounding capabilities (e.g., VideoChat, Video-ChatGPT, Video-LLaMA) or do not utilize the audio-signals for better video understanding (e.g., Video-ChatGPT). Addressing these gaps, we propose Video-LLaVA, the first LMM with pixel-level grounding capability, integrating audio cues by transcribing them into text to enrich video-context understanding. Our framework uses an off-the-shelf tracker and a novel grounding module, enabling it to spatially and temporally localize objects in videos following user instructions. We evaluate Video-LLaVA using video-based generative and question-answering benchmarks and introduce new benchmarks specifically designed to measure prompt-based object grounding performance in videos. Further, we propose the use of Vicuna over GPT-3.5, as utilized in Video-ChatGPT, for video-based conversation benchmarking, ensuring reproducibility of results which is a concern with the proprietary nature of GPT-3.5. Our framework builds on SoTA image-based LLaVA model and extends its advantages to the video domain, delivering promising gains on video-based conversation and grounding tasks. Project Page: https://github.com/mbzuai-oryx/Video-LLaVA

翻译：将基于图像的大规模多模态模型（LMM）扩展到视频领域，因视频数据固有的复杂性而充满挑战。现有将图像LMM推广至视频的方法，或缺乏定位能力（如VideoChat、Video-ChatGPT、Video-LLaMA），或未能利用音频信号提升视频理解（如Video-ChatGPT）。针对上述不足，我们提出Video-LLaVA——首个具备像素级定位能力的LMM，通过将音频转录为文本整合音频线索，从而丰富视频上下文理解。我们的框架采用现成追踪器与新型定位模块，能够根据用户指令在视频中对目标进行空间与时间定位。我们基于视频生成与问答基准评估Video-LLaVA，并引入针对视频中指令驱动目标定位性能评估的新基准。此外，我们提出采用Vicuna替代Video-ChatGPT中使用的GPT-3.5进行视频对话基准测试，以解决GPT-3.5专有性导致的结果可复现性问题。本框架在现有最先进的图像LLaVA模型基础上构建，将其优势拓展至视频领域，在视频对话与定位任务中取得显著性能提升。项目主页：https://github.com/mbzuai-oryx/Video-LLaVA