Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts
This work addresses the problem of overfitting and cross-modal gaps in video question answering for researchers and practitioners, though it is incremental as it builds on existing prompt learning methods.
The paper tackles the challenge of adapting pretrained vision-language models to video question answering with limited data, achieving superior performance and parameter efficiency in zero-shot and few-shot settings.
Recent vision-language models are driven by large-scale pretrained models. However, adapting pretrained models on limited data presents challenges such as overfitting, catastrophic forgetting, and the cross-modal gap between vision and language. We introduce a parameter-efficient method to address these challenges, combining multimodal prompt learning and a transformer-based mapping network, while keeping the pretrained models frozen. Our experiments on several video question answering benchmarks demonstrate the superiority of our approach in terms of performance and parameter efficiency on both zero-shot and few-shot settings. Our code is available at https://engindeniz.github.io/vitis.