MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
Published in
arXiv.org(2024)External Links:
TL
TL;DR
This paper introduces MiniGPT4-Video, a multimodal Large Language Model (LLM) designed specifically for video understanding that does not only consider visual content but also incorporates textual conversations, allowing the model to effectively answer queries involving both visual and text components.
Abstract
This paper introduces MiniGPT4-Video, a multimodal Large Language Model (LLM) designed specifically for video understanding. The model is capable of processing both temporal visual and textual data, making it adept at understanding the complexities of videos. Building upon the success of MiniGPT-v2, which excelled in translating visual features into the LLM space for single images and achieved impressive results on various image-text benchmarks, this paper extends the model's capabilities to process a sequence of frames, enabling it to comprehend videos. MiniGPT4-video does not only consider visual content but also incorporates textual conversations, allowing the model to effectively answer queries involving both visual and text components. The proposed model outperforms existing state-of-the-art methods, registering gains of 4.22%, 1.13%, 20.82%, and 13.1% on the MSVD, MSRVTT, TGIF, and TVQA benchmarks respectively. Our models and code have been made publicly available here https://vision-cair.github.io/MiniGPT4-video/
References33 items
1
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models
2
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
3
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
4
Mistral 7B
5