computer-vision-11
Few-shot Video Question Answering
3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in few-shot-video-question-answering-23
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find few-shot-video-question-answering-23 models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts
Yannis Avrithis, Deniz Engin•Tue Sep 26 2023
A parameter-efficient method is introduced, combining multimodal prompt learning and a transformer-based mapping network, while keeping the pretrained models frozen to address challenges such as overfitting, catastrophic forgetting, and the cross-modal gap between vision and language.
10