Question-Instructed Visual Descriptions for Zero-Shot Video Question Answering

arXiv:2402.10698v1 Announce Type: new
Abstract: We present Q-ViD, a simple approach for video question answering (video QA), that unlike prior methods, which are based on complex architectures, computationally expensive pipelines or use closed models like GPTs, Q-ViD relies on a single instruction-aware open vision-language model (InstructBLIP) to tackle videoQA using frame descriptions. Specifically, we create captioning instruction prompts that rely on the target questions about the videos and leverage InstructBLIP to obtain video frame captions that are useful to the …

abstract architectures arxiv cs.cv gpts language language model pipelines prior question question answering simple type video vision visual zero-shot