Recurrent Instance Segmentation using Sequences of Referring Expressions

Alba Maria Hererra-Palacio
Alba Maria Hererra-Palacio
Carina Silberer
Carina Silberer
Ionut-Teodor Sorodoc
Ionut-Teodor Sorodoc
Gemma Boleda
Gemma Boleda
Xavier Giró i Nieto
Xavier Giró i Nieto

ViGIL@NeurIPS, 2019.

Cited by: 0|Bibtex|Views4|Links
EI

Abstract:

The goal of this work is to segment the objects in an image that are referred to by a sequence of linguistic descriptions (referring expressions). We propose a deep neural network with recurrent layers that output a sequence of binary masks, one for each referring expression provided by the user. The recurrent layers in the architecture...More

Code:

Data:

Your rating :
0

 

Tags
Comments