AI RESEARCH
Mobile-VideoGPT: Fast and Accurate Model for Mobile Video Understanding
arXiv CS.CV
•
ArXi:2503.21782v2 Announce Type: replace Video understanding models often struggle with high computational requirements, extensive parameter counts, and slow inference speed, making them inefficient for practical use. To tackle these challenges, we propose Mobile-VideoGPT, an efficient multimodal framework designed to operate with fewer than a billion parameters. Unlike traditional video large multimodal models (LMMs), Mobile-VideoGPT consists of lightweight dual visual encoders, efficient projectors, and a small language model (SLM), enabling real-time throughput.