MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
This work addresses video understanding for multimodal AI applications, representing an incremental advancement by adapting an existing image-based model to video.
The paper tackles video understanding by extending MiniGPT-v2 to process sequences of frames and incorporate textual conversations, achieving gains of 4.22%, 1.13%, 20.82%, and 13.1% on MSVD, MSRVTT, TGIF, and TVQA benchmarks.
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/