PG-Video-LLaVA: Pixel Grounding Large Video-Language Models

Anonymous

Abstract: Extending image-based Large Multimodal Models (LMMs) to videos is challenging due to the inherent complexity of video data. The recent approaches extending image-based LMMs 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 PG-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 localize objects in videos following user instructions. We evaluate PG-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 using open-source Vicuna LLM for video-based conversation benchmarking, as opposed to GPT-3.5 utilized in Video-ChatGPT, 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. Our codes, pretrained models, and interactive demos will be made publicly available.

Paper Type: long

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Contribution Types: Model analysis & interpretability, Publicly available software and/or pre-trained models

Languages Studied: English