computer-vision-3
Reference Expression Generation
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 reference-expression-generation-3
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find reference-expression-generation-3 models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
Towards Unifying Reference Expression Generation and Comprehension
Tao Kong, Xiaojie Wang, Jiaan Wang, Duo Zheng, Ya Jing•Sun Oct 23 2022
A unified model forREG and REC is proposed, named UniRef, which outperforms previous state-of-the-art methods on both REG and REC and proposes Vision-conditioned Masked Language Modeling and Text-Conditioned Region Prediction to pre-train UniRef model on multi-granular corpora.
9