Robuta

https://openreview.net/forum?id=Kn4p6ebC-A&referrer=%5Bthe%20profile%20of%20Xiantong%20Zhen%5D(%2Fprofile%3Fid%3D~Xiantong_Zhen1)
The task of multimodal referring expression comprehension (REC), aiming at localizing an image region described by a natural language expression, has recently...
commonsense knowledgereferring expressioncktransformerenhanced
https://deepai.org/publication/multi-task-collaborative-network-for-joint-referring-expression-comprehension-and-segmentation
03/19/20 - Referring expression comprehension (REC) and segmentation (RES) are two highly-related tasks, which both aim at identifying the re...
multi taskcollaborative networkreferring expressionjointcomprehension