Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts
2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS, ICCVW(2023)
Abstract
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.
MoreTranslated text
Key words
video,zero-shot,few-shot,multi-modal
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined