scholarly journals Visual saliency-based bas-relief generation with symmetry composition rule

2018 ◽  
Vol 29 (3-4) ◽  
pp. e1815
Author(s):  
Tingting Li ◽  
Liying Yang ◽  
Meili Wang ◽  
Yuling Fan ◽  
Feiyu Zhang ◽  
...  

2014 ◽  
Vol 35 (7) ◽  
pp. 1636-1643
Author(s):  
Xiao-liang Qian ◽  
Lei Guo ◽  
Jun-wei Han ◽  
Xin-tao Hu ◽  
Gong Cheng


2021 ◽  
Vol 11 (16) ◽  
pp. 7217
Author(s):  
Cristina Luna-Jiménez ◽  
Jorge Cristóbal-Martín ◽  
Ricardo Kleinlein ◽  
Manuel Gil-Martín ◽  
José M. Moya ◽  
...  

Spatial Transformer Networks are considered a powerful algorithm to learn the main areas of an image, but still, they could be more efficient by receiving images with embedded expert knowledge. This paper aims to improve the performance of conventional Spatial Transformers when applied to Facial Expression Recognition. Based on the Spatial Transformers’ capacity of spatial manipulation within networks, we propose different extensions to these models where effective attentional regions are captured employing facial landmarks or facial visual saliency maps. This specific attentional information is then hardcoded to guide the Spatial Transformers to learn the spatial transformations that best fit the proposed regions for better recognition results. For this study, we use two datasets: AffectNet and FER-2013. For AffectNet, we achieve a 0.35% point absolute improvement relative to the traditional Spatial Transformer, whereas for FER-2013, our solution gets an increase of 1.49% when models are fine-tuned with the Affectnet pre-trained weights.



2021 ◽  
Author(s):  
Sai Phani Kumar Malladi ◽  
Jayanta Mukhopadhyay ◽  
Chaker Larabi ◽  
Santanu Chaudhury


Author(s):  
Shenyi Qian ◽  
Yongsheng Shi ◽  
Huaiguang Wu ◽  
Jinhua Liu ◽  
Weiwei Zhang


Author(s):  
Wenxia Zhang ◽  
Chunguang Wang ◽  
Haichao Wang ◽  
Xiaofei Yin
Keyword(s):  


Author(s):  
Luis A. Leiva ◽  
Yunfei Xue ◽  
Avya Bansal ◽  
Hamed R. Tavakoli ◽  
Tuðçe Köroðlu ◽  
...  


Author(s):  
Hamed Rezazadegan Tavakoli ◽  
Ali Borji ◽  
Juho Kannala ◽  
Esa Rahtu


Sign in / Sign up

Export Citation Format

Share Document