Discovering Class-Specific Spatial Layouts for Scene Recognition
Scene image is a spatial composition of objects and background contexts and finding discriminative spatial layouts is critical for scene recognition. In this letter, we propose an ℓ1-regularized max-margin formulation to discover class-specific spatial layouts by jointly learning the image classifie...
Saved in:
Main Authors: | Weng, Chaoqun, Wang, Hongxing, Yuan, Junsong, Jiang, Xudong |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Article |
Language: | English |
Published: |
2017
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/82238 http://hdl.handle.net/10220/43502 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Real scene sign recognition
by: Li, L., et al.
Published: (2013) -
THE ROLE OF TEXTURE IN INDOOR SCENE RECOGNITION
by: SHAHZOR AHMAD
Published: (2016) -
Scene recognition by semantic visual words
by: Farahzadeh, Elahe, et al.
Published: (2015) -
HMM-based multi oriented text recognition in natural scene image
by: Roy, S., et al.
Published: (2014) -
Image-to-character-to-word transformers for accurate scene text recognition
by: Xue, Chuhui, et al.
Published: (2023)