FPAN: Fine-grained and progressive attention localization network for data retrieval
Genre
Pre-printDate
2018-10-09Author
Chen, SSong, B
Guo, J
Zhang, Y
Du, X
Guizani, M
Subject
Query-based object localizationFine-grained attention
Progressive attention
Unified framework
Fully convolution localization network
Permanent link to this record
http://hdl.handle.net/20.500.12613/4390
Metadata
Show full item recordDOI
10.1016/j.comnet.2018.07.011Abstract
© 2018 Elsevier B.V. The localization of the target object for data retrieval is a key issue in the Intelligent and Connected Transportation Systems (ICTS). However, due to the lack of intelligence in the traditional transportation system, it takes a lot of resources to manually retrieve and locate the queried objects from a large number of images. In order to solve this issue, we propose an effective method for query-based object localization, which uses artificial intelligence techniques to automatically locate the queried object in complex backgrounds. The proposed method is termed as Fine-grained and Progressive Attention Localization Network (FPAN), which uses an image and a queried object as input to accurately locate the target object in the image. Specifically, the fine-grained attention module is naturally embedded into each layer of a convolution neural network (CNN), thereby gradually suppressing the regions that are irrelevant to the queried object and eventually focusing attention on the target area. We further employ top-down attentions fusion algorithm operated by a learnable cascade up-sampling structure to establish the connection between the attention map and the exact location of the queried object in the original image. Furthermore, the FPAN is trained by multi-task learning with box segmentation loss and cosine loss. At last, we conduct comprehensive experiments on both queried-based digit localization and object tracking with synthetic and benchmark datasets. The experimental results show that our algorithm is far superior than other algorithms on the synthesis datasets and outperforms most existing trackers on the OTB and VOT datasets.Citation to related work
Elsevier BVHas part
Computer NetworksADA compliance
For Americans with Disabilities Act (ADA) accommodation, including help with reading this content, please contact scholarshare@temple.eduae974a485f413a2113503eed53cd6c53
http://dx.doi.org/10.34944/dspace/4372