Large Language Model with Curriculum Reasoning for Visual Concept Recognition
Visual concept recognition aims to capture the basic attributes of an image and reason
about the relationships among them to determine whether the image satisfies a certain …
about the relationships among them to determine whether the image satisfies a certain …
Neighbor Does Matter: Curriculum Global Positive-Negative Sampling for Vision-Language Pre-training
Sampling strategies have been widely adopted in Vision-Language Pre-training (VLP) and
have achieved great success recently. However, the sampling strategies adopted by current …
have achieved great success recently. However, the sampling strategies adopted by current …