[A-14] Smart Info-media System

2:15 PM - 2:30 PM JST(5:15 AM - 5:30 AM UTC)Candidate for Academic Incentive Award

[A-14-06] Object-guided Visual Segmentation & Compression for Improving VLM on Streaming Video QA

◎Zhi Li¹, Yanan Wang¹, Hao Niu¹, Julio Vizcarra¹, Masato Taya¹ (1. KDDI Research Inc.)

Keywords:

Multi-modal Large Language Model,Streaming Video Question Answering