COCOQA
Emerging4papers using it
2017first seen
COCOQA is a visual question answering dataset that contains images paired with questions and answers, used to evaluate the spatial reasoning capabilities of vision language models.
Papers using COCOQA (4)
- ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision Language ModelsStitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial UnderstandingCo-attending Free-form Regions and Detections with Multi-modal
Multiplicative Feature Embedding for Visual Question AnsweringEnhancing Visual Question Answering through Ranking-Based Hybrid
Training and Multimodal Fusion