مؤتمر
SaltiNet: scan-path prediction on 360 degree images using saliency volumes
| العنوان: | SaltiNet: scan-path prediction on 360 degree images using saliency volumes |
|---|---|
| المؤلفون: | Assens, Marc, Giró Nieto, Xavier, McGuinness, Kevin, O'Connor, Noel |
| المساهمون: | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions, Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo |
| بيانات النشر: | IEEE Press |
| سنة النشر: | 2018 |
| المجموعة: | Universitat Politècnica de Catalunya (UPC): Tesis Doctorals en Xarxa (TDX) / Theses and Dissertations Online |
| مصطلحات موضوعية: | Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Representació del coneixement, Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo, Image processing--Digital techniques, Artificial vision, Artificial intelligence, Neural networks (Computer science), Computer vision, saliency prediction, scanpath, eye gaze, deep learning, convolutional neural networks, Imatges -- Processament -- Tècniques digitals, Visió artificial (Robòtica), Visió per ordinador, Intel·ligència artificial, Xarxes neuronals (Informàtica) |
| الوصف: | We introduce SaltiNet, a deep neural network for scan-path prediction trained on 360-degree images. The model is based on a temporal-aware novel representation of saliency information named the saliency volume. The first part of the network consists of a model trained to generate saliency volumes, whose parameters are fit by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency volumes. Sampling strategies over these volumes are used to generate scan-paths over the 360-degree images. Our experiments show the advantages of using saliency volumes, and how they can be used for related tasks. Our source code and trained models available at https://github.com/massens/saliency-360salient-2017Test. ; Peer Reviewed ; Postprint (published version) |
| نوع الوثيقة: | conference object |
| وصف الملف: | 8 p. |
| اللغة: | English |
| ردمك: | 978-1-5386-1034-3 1-5386-1034-5 |
| العلاقة: | http://ieeexplore.ieee.org/document/8265485Test/; info:eu-repo/grantAgreement/MINECO/PE2013-2016/TEC2013-43935-R; info:eu-repo/grantAgreement/MINECO/PE2016-2020/ TEC2016-75976-R; Assens, M., Giro, X., McGuinness, K., O'Connor, N. SaltiNet: scan-path prediction on 360 degree images using saliency volumes. A: International Workshop on Egocentric Perception, Interaction and Computing. "2017 IEEE International Conference on Computer Vision Workshops (ICCVW)". IEEE Press, 23/01/2018, p. 2331-2338.; https://arxiv.org/abs/1707.03123Test; http://hdl.handle.net/2117/114891Test |
| DOI: | 10.1109/ICCVW.2017.275 |
| الإتاحة: | https://doi.org/10.1109/ICCVW.2017.275Test https://arxiv.org/abs/1707.03123Test http://hdl.handle.net/2117/114891Test |
| حقوق: | Open Access |
| رقم الانضمام: | edsbas.3ECEE50F |
| قاعدة البيانات: | BASE |
| ردمك: | 9781538610343 1538610345 |
|---|---|
| DOI: | 10.1109/ICCVW.2017.275 |