PPT-Deep Learning for Expression Recognition in Image Sequences

Deep Learning for Expression Recognition in Image Sequences Daniel Natanael García Zapata Tutors Dr Sergio Escalera Dr Gholamreza Anbarjafari April 27 2018 Introduction and Goals Introduction Dennis Hamester et al Face ExpressionRecognition with a 2Channel ConvolutionalNeural Network International Joint Conference on Neural Networks IJCNN 2015. Common Core State Standards. MACC.7.EE.1.1. Apply properties of operations as strategies to add, subtract, factor, and expand linear expressions with rational coefficients.. MACC.7.EE.1.2. Understand that rewriting an expression in different forms in a problem context can shed light on the problem and how the quantities in it are related.. Jakob Verbeek. LEAR team, INRIA Rhône-Alpes. Outline of this talk. Motivation for “weakly supervised” learning. Learning MRFs for image region labeling from weak supervision. Models, Learning, Results. Presenter: . Yanming. . Guo. Adviser: Dr. Michael S. Lew. Deep learning. Human. Computer. 1:4. Human . v.s. . Computer. Deep learning. Human. Computer. 1:4. Human . v.s. . Computer. Deep Learning. Why better?. 1. Speech Recognition and HMM Learning. Overview of speech recognition approaches. Standard Bayesian Model. Features. Acoustic Model Approaches. Language Model. Decoder. Issues. Hidden Markov Models. Yuchen Fan, Matt Potok, Christopher Shroba. Motivation. Text-to-Speech. Accessibility features for people with little to no vision, or people in situations where they cannot look at a screen or other textual source. Linda Shapiro. CSE 455. 1. Face recognition: once you’ve detected and cropped a face, try to recognize it. Detection. Recognition. “Sally”. 2. Face recognition: overview. Typical scenario: few examples per face, identify or verify test example. 2. Question to Consider. What are the key challenges police officers face when dealing with persons in behavioral crisis?. 3. Recognizing a. Person in Crisis. Crisis Recognition. 4. Behavioral Crisis: A Definition. Badruz. . Nasrin. Bin Basri. 1051101534.  . Supervisor : . Mohd. . Haris. Lye Abdullah. 1. Contents. Introduction. 1. Literature review  . 2. Method . Used.  . 3. Experiment and Result. 4. Future works. New-Generation Models & Methodology for Advancing . AI & SIP. Li Deng . Microsoft Research, Redmond, . USA. Tianjin University, July 2-5, 2013. (including joint work with colleagues at MSR, U of Toronto, etc.) . New-Generation Models & Methodology for Advancing . Speech Technology . and Information Processing. Li Deng . Microsoft Research, Redmond, . USA. CCF, . Beijing. , July . 8. , 2013. (including joint work with colleagues at MSR, U of Toronto, etc.) . Drosophila. Embryos using . lacZ. Transgenes. June 18. th. ABLE 2014. University of Oregon, Eugene. Cathy Silver Key. Julie Gates. Jessica Sawyer. Kirsten . Guss. Acknowledgements. Funding from . Roberta . Asmitha Rathis. Why Bioinformatics?. Protein structure . Genetic Variants . Anomaly classification . Protein classification. Segmentation/Splicing . Why is Deep Learning beneficial?. scalable with large datasets and are effective in identifying complex patterns from feature-rich datasets . Linda Shapiro. ECE P 596. 1. What’s Coming. Review of . Bakic. flesh . d. etector. Fleck and Forsyth flesh . d. etector. Review of Rowley face . d. etector. Overview of. . Viola Jones face detector with . New-Generation Models & Methodology for Advancing Speech Technology. Li Deng . Microsoft Research, Redmond, USA. Keynote at . Odyssey Speaker/Language Recognition Workshop. Singapore, June. 26, 2012.