1,764 Hits in 5.1 sec

Parallel implementation of a spatio-temporal visual saliency model

A. Rahman, D. Houzet, D. Pellerin, S. Marat, N. Guyader
2010 Journal of Real-Time Image Processing  
Some of these models concerns visual saliency which is potentially very interesting in a lot of applications like robotics, image analysis, compression, video indexing.  ...  Among all the existing models, we have chosen a spatio-temporal one combining static and dynamic information.  ...  Fig. 1 1 The spatio-temporal visual saliency model to develop and manage.  ... 
doi:10.1007/s11554-010-0164-7 fatcat:cwt6az5oc5ggldmqbzg3zza6ku

GPU implementation of motion estimation for visual saliency

Anis Rahman, Dominique Houzet, Denis Pellerin, Lionel Agud
2010 2010 Conference on Design and Architectures for Signal and Image Processing (DASIP)  
In this paper, we discuss a spatio-temporal visual saliency model where the visual information contained in videos is divided into two types: static and dynamic that are processed by two separate pathways  ...  The implementation involves a number of code and memory optimizations to get the performance gains, resultantly materializing real-time video analysis capability for the visual saliency model.  ...  After the parallel implementation of the spatio-temporal visual saliency model, we used OpenCV for interfacing with webcam and videos to demonstrate the real-time processing of the model.  ... 
doi:10.1109/dasip.2010.5706268 dblp:conf/dasip/RahmanHPA10 fatcat:ybwoaxyyyzeflnkdcijejk6b5y

Spatio-Temporal Saliency Perception via Hypercomplex Frequency Spectral Contrast

Ce Li, Jianru Xue, Nanning Zheng, Xuguang Lan, Zhiqiang Tian
2013 Sensors  
In this paper, we propose a novel spatio-temporal saliency perception method based on spatio-temporal hypercomplex spectral contrast (HSC).  ...  Salient object perception is the process of sensing the salient information from the spatio-temporal visual scenes, which is a rapid pre-attention mechanism for the target location in a visual smart sensor  ...  The authors would also like to gratefully acknowledge the financial support from the National Basic Research Program of China (973 Program) under Grant No. 2010CB327902 and the NSFC Nos.90920301 and 61273252  ... 
doi:10.3390/s130303409 pmid:23482090 pmcid:PMC3658753 fatcat:h5riehkwdbhatpgukryewycm5m

A Neuromorphic Proto-Object Based Dynamic Visual Saliency Model with an FPGA Implementation [article]

Jamal Lottier Molin, Chetan Singh Thakur, Ralph Etienne-Cummings, Ernst Niebur
2020 arXiv   pre-print
In this paper, we first present a neuromorphic, bottom-up, dynamic visual saliency model based on the notion of proto-objects.  ...  This neuromorphic model outperforms state-of-the-art dynamic visual saliency models in predicting human eye fixations on a commonly used video dataset with associated eye tracking data.  ...  Fig. 4 . 4 Block diagram of the complete FPGA implementation of our Proto-object Based Dynamic Visual Saliency Model. a) P1: Transmit Spatio-temporal Feature Extraction Output b) P2: Generate Frame Pyramid  ... 
arXiv:2002.11898v3 fatcat:zpg34vb5evd6plyjimvwbg6st4

Spatio-temporal combination of saliency maps and eye-tracking assessment of different strategies

C. Chamaret, J.C. Chevet, O. Le Meur
2010 2010 IEEE International Conference on Image Processing  
The modeling of the human visual attention into a computational attention model leads to the split of visual features into several independent channels.  ...  Several strategies of cue combination are proposed in this paper for the spatial cues as well as the temporal saliency.  ...  A biological model comprises a number of parallel channels for processing different visual features such as the luminance, the orientation and the color.  ... 
doi:10.1109/icip.2010.5651381 dblp:conf/icip/ChamaretCM10 fatcat:nmkvnpvbsbadrhopm5tfsjjzne

Color Information In A Model Of Saliency

Nathalie Guyader, Shahrbanoo Hamel, D. Houzet, D. Pellerin
2014 Zenodo  
Publication in the conference proceedings of EUSIPCO, Lisbon, Portugal, 2014  ...  a master spatio-temporal saliency map per video frame.  ...  [1] spatio-temporal saliency model, the chrominance processing steps first introduced by Ho-Phuoc et al. [23] .  ... 
doi:10.5281/zenodo.44191 fatcat:tpuoqlfonnhuvlfpfmlhzw7shy

A perceptually based spatio-temporal computational framework for visual saliency estimation

Petros Koutras, Petros Maragos
2015 Signal processing. Image communication  
The purpose of this paper is to demonstrate a perceptually based spatio-temporal computational framework for visual saliency estimation.  ...  These volumes are fused for computing a single saliency map and can detect spatiotemporal phenomena that static saliency models cannot find.  ...  Acknowledgments This research work was supported by the project "COGNIMUSE" which is implemented under the "ARIS-TEIA" Action of the Operational Program Education and Lifelong Learning and is co-funded  ... 
doi:10.1016/j.image.2015.08.004 fatcat:kha3povnbna5lbecznl2syefqm

Spatio-Temporal Self-Attention Network for Video Saliency Prediction [article]

Ziqiang Wang, Zhi Liu, Gongyang Li, Tianhong Zhang, Lihua Xu, Jijun Wang
2021 arXiv   pre-print
To overcome this limitation, we propose a novel Spatio-Temporal Self-Attention 3D Network (STSANet) for video saliency prediction, in which multiple Spatio-Temporal Self-Attention (STSA) modules are employed  ...  time of a video.  ...  In computer vision, modeling the visual attention mechanism is a fundamental research topic, named saliency prediction (SP) or fixation prediction, which aims to deduce the visual saliency degree of each  ... 
arXiv:2108.10696v1 fatcat:llbizroitvhy5cqzlxnmhzi3ry

Efficient Online Spatio-Temporal Filtering for Video Event Detection [chapter]

Xinchen Yan, Junsong Yuan, Hui Liang
2015 Lecture Notes in Computer Science  
We propose a novel spatio-temporal filtering technique to improve the per-pixel prediction map, by leveraging the spatio-temporal smoothness of the video signal.  ...  Different from previous techniques that perform spatio-temporal filtering in an offline/batch mode, e.g., through graphical model, our filtering can be implemented online and in real-time, with provable  ...  Discovering events based on accumulated saliency parallels the theory that selective visual attention results from competition among multiple responses in visual cortex [36, 5] . Method.  ... 
doi:10.1007/978-3-319-16178-5_54 fatcat:zrjyxujpcrbohdyashk7s5wuou

Audio-Visual Collaborative Representation Learning for Dynamic Saliency Prediction [article]

Hailong Ning, Bin Zhao, Zhanxuan Hu, Lang He, Ercheng Pei
2022 arXiv   pre-print
DSP models.  ...  Thirdly, a collaborative integration part is devised to adaptively aggregate audio-visual information and center-bias prior to generate the final saliency map.  ...  Audio-Visual Encoding The audio-visual encoding part consists of two paralleled branches for encoding the original data as audio semantic features and spatio-temporal visual features, respectively.  ... 
arXiv:2109.08371v3 fatcat:4uqa4l25mjaztppresigt6jd6a

Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform

Chenlei Guo, Qi Ma, Liming Zhang
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
The added motion dimension allows the phase spectrum to represent spatio-temporal saliency in order to engage in attention selection for videos as well as images.  ...  Recently a simple and fast approach based on Fourier transform called spectral residual (SR) was proposed, which used SR of the amplitude spectrum to obtain the saliency map.  ...  Incorporating motion into these models is a challenging task that motivates us to develop a novel method to generate spatio-temporal saliency map.  ... 
doi:10.1109/cvpr.2008.4587715 dblp:conf/cvpr/GuoMZ08 fatcat:25y6ldrrf5byzflfnuc2khutri

Contribution of Color Information in Visual Saliency Model for Videos [chapter]

Shahrbanoo Hamel, Nathalie Guyader, Denis Pellerin, Dominique Houzet
2014 Lecture Notes in Computer Science  
We investigated the contribution of color information in a bottom-up visual saliency model.  ...  Much research has been concerned with the contribution of the low level features of a visual scene to the deployment of visual attention.  ...  Fig. 1 . 1 The spatio-temporal saliency model.  ... 
doi:10.1007/978-3-319-07998-1_24 fatcat:3l3dkqtrmncq3mgnvuaixzq3gm

Spatio-temporal salience based video quality assessment

Xinbo Gao, Ni Liu, Wen Lu, Dacheng Tao, Xuelong Li
2010 2010 IEEE International Conference on Systems, Man and Cybernetics  
Keywords-Video quality assessment, human visual system, visual attention, spatio-temporal salience, motion I.  ...  The proposed method first uses the VA model to obtain visual saliency map of the distorted video, including color, intensity and motion.  ...  CONCLUSION This paper describes a video quality assessment based on spatio-temporal salience.  ... 
doi:10.1109/icsmc.2010.5642429 dblp:conf/smc/GaoLLTL10 fatcat:46brty63gvhsnbpmdwfxpk27ly

A Novel Spatio-Temporal 3D Convolutional Encoder-Decoder Network for Dynamic Saliency Prediction

Hao Li, Fei Qi, Guangming Shi
2021 IEEE Access  
INDEX TERMS Visual attention, dynamic saliency prediction, 3D fully convolutional networks, spatio-temporal features.  ...  As human beings are living in an always changing environment, predicting saliency maps from dynamic visual stimulus is of importance for modeling human visual system.  ...  IMPLEMENTATION DETAILS The proposed model takes a video clip with T = 32 continuous frames as input to predict the saliency map of the last frame.  ... 
doi:10.1109/access.2021.3063372 fatcat:ulowudxbm5cjpmzsnwnpvwxgvy

Spatio-temporal saliency based on rare model

Marc Decombas, Nicolas Riche, Frederic Dufaux, Beatrice Pesquet-Popescu, Matei Mancas, Bernard Gosselin, Thierry Dutoit
2013 2013 IEEE International Conference on Image Processing  
In this paper, a new spatio-temporal saliency model is presented.  ...  Based on the idea that both spatial and temporal features are needed to determine the saliency of a video, this model builds upon the fact that locally contrasted and globally rare features are salient  ...  INTRODUCTION The aim of visual saliency models is to automatically predict human attention.  ... 
doi:10.1109/icip.2013.6738712 dblp:conf/icip/DecombasRDPMGD13 fatcat:3rawg22l65efxilyplg2eck7ui
« Previous Showing results 1 — 15 out of 1,764 results