PPT-Sparsity and Saliency

Xiaodi Hou KLab Computation and Neural Systems California Institute of Technology for the Crash Course on Visual Saliency Modeling Behavioral Findings and Computational Models CVPR 2013 Schedule. 800 Dongchuan Road Shanghai httpbcmisjtueducn houxiaodi zhanglqcssjtueducn Abstract The ability of human visual system to detect visual saliency is extraordinarily fast and reliable However co m putational modeling of this basic intelligent behavior We joint ly consider the appearance divergence and spatial distri bution of salient objects and the background The virtual boundary nodes are chosen as the absorbing nodes in a Markov chain and the absorbed time from each transient node to boundary com Abstract Generic object level saliency detection is important for many vision tasks Previous approaches are mostly built on the prior that ap pearance contrast between objects and backgrounds is high Although various computational models have bee Presenter: Wei Wang. Institute of Digital Media, . PKU . Outline. Introduction to visual attention. The . computational . models of visual attention. The state-of-the-art models . of visual attention. Felix Lee. HPC I. 28.10.2013. Real-time Live Panoramic Video. OMNICAM. real-time acquisition. warping & stitching. blending and rendering of 6 HD video streams. one panoramic video of . 7k x 2k . TVCG 2013. Sungkil. Lee, Mike Sips, and Hans-Peter Seidel. Introduction. Class Visibility. Optimization . Example. Conclusion. Outline. Principles of effective color palettes (Trumbo, 1981) . Order: colors chosen to present an ordered statistical variables should be perceived as preserving that order. . Stas. . Goferman. Lihi. . Zelnik. -Manor. Ayellet. Tal. What is saliency?. …. Please describe this picture. Picture description. Man in a flower field. In the fields. Spring blossom. Please describe this picture. . Junzhou. Huang . Xiaolei. Huang . Dimitris. Metaxas . Rutgers University Lehigh University Rutgers University. Outline. Problem: Applications where the useful information is very less compared with the given data . Sabareesh Ganapathy. Manav Garg. Prasanna. . Venkatesh. Srinivasan. Convolutional Neural Network. State of the art in Image classification. Terminology – Feature Maps, Weights. Layers - Convolution, . . Junzhou. Huang . Xiaolei. Huang . Dimitris. Metaxas . Rutgers University Lehigh University Rutgers University. Outline. Problem: Applications where the useful information is very less compared with the given data . : Advanced . Computer. Graphics. Perception. in 3D . Computer Graphics. Motivation. Çok. rendering . yavaş. . olur. ! (told by?). Take perception into account. Don’t waste resources. Render less. SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks. 9 authors @ NVIDIA, MIT, Berkeley, Stanford. ISCA . 2017. Convolution operation. Reuse. Memory: size vs. access energy. Dataflow decides reuse. Afsaneh . Asaei. Joint work with: . Mohammad . Golbabaee. ,. Herve. Bourlard, . Volkan. . Cevher. φ. 21. φ. 52. s. 1. s. 2. s. 3. . s. 4. s. 5. x. 1. x. 2. φ. 11. φ. 42. 2. Speech . Separation Problem. Applications. 报告人：程明明. 南开大学、计算机与控制工程学. 院. http://mmcheng.net/. Contents. Global . contrast based salient region . detection. ,. PAMI 2014. BING: Binarized Normed Gradients for Objectness Estimation at .