はてなブックマーク

🏆 "The VQA Series of Challenges" has been recognized with the 2025 Mark Everingham Prize for "stimulating a new strand of vision and language research". Thank you to the PAMI TC committee! VQA is a new dataset containing open-ended questions about images. These questions require an understanding of vision, language and commonsense knowledge to answer. 265,016 images (COCO and abstract scenes) At