Paired cross-modal data augmentation for fine-grained image-to-text retrieval
This paper investigates an open research problem of generating text-image pairs to improve the training of fine-grained image-to-text cross-modal retrieval task, and proposes a novel framework for paired data augmentation by uncovering the hidden semantic information of StyleGAN2 model. Specific...
Saved in:
Main Authors: | Wang, Hao, Lin, Guosheng, Hoi, Steven C. H., Miao, Chunyan |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/164145 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Learning structural representations for recipe generation and food retrieval
by: Wang, Hao, et al.
Published: (2022) -
Adaptation of language models via text augmentation
by: Prachaseree, Chaiyasait
Published: (2023) -
Cycle-consistent inverse GAN for text-to-image synthesis
by: Wang, Hao, et al.
Published: (2022) -
Deep learning-based text augmentation for named entity recognition
by: Surana, Tanmay
Published: (2023) -
Imaged document text retrieval without OCR
by: Tan, C.L., et al.
Published: (2013)