In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option severely hurts the detection performance. This paper focuses on boosting the performance of a …
Structured representations of images according to visual relationships are beneficial for many vision and vision-language applications. However, current human-annotated visual relationship datasets suffer from the long-tailed predicate distribution …
Scene graph generation has received growing attention with advancement image understanding tasks such as object detection, attributes and relationship prediction, etc. However, existing datasets are biased in terms of object and relationship labels, …