HIGHLIGHTS
- who: PENG YANG and collaborators from the School of Information Engineering, Nanjing Audit University, Nanjing, China have published the research work: Instance Segmentation Network With Self-Distillation for Scene Text Detection, in the Journal: (JOURNAL)
- what: The authors propose an instance segmentation network (ISNet) which simultaneously generates prototype masks and per-instance mask coefficients. Although lots of achievements have been made in this field, the authors still face a series of difficulties due to the following reasons. (a) Scene texts are often scattered in an image, and there is no prior information (different from document . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.