PPT-Large Scale Visual Recognition Challenge 2011

Alex Berg Stony Brook Jia Deng Stanford amp Princeton Sanjeev Satheesh Stanford Hao Su Stanford FeiFei Li Stanford LSVRC 2011 Car Categorization Localization Car Large. CSE P 576. Larry Zitnick (. larryz@microsoft.com. ). 20,000 images of Rome. =. ?. Large scale matching. How do we match millions or billions of images in under a second?. Is it even possible to store the information necessary?. Weiqiang. . Ren. , Chong Wang, . Yanhua. Cheng, . Kaiqi. . Huang, . Tieniu. . Tan. {. wqren,cwang,yhcheng,kqhuang,tnt. }@nlpr.ia.ac.cn. Task2 : Classification + Localization. Task 2b: . Classification + localization . By. Chi . Bemieh. . Fule. August 6, 2013. THESIS PRESENTATION . Outline. . of. . today’s. presentation. Justification of the study. Problem . statement. Hypotheses. Conceptual. . framework. Research . Alex Berg. Stony Brook University. I work on recognition:. features – action recognition – alignment – detection – attributes – hierarchical image classification & retrieval. + machine learning for large scale recognition. Kuan-Chuan. Peng. Tsuhan. Chen. 1. Introduction. Breakthrough progress in object classification.. 2. O. . Russakovsky. . et al. . ImageNet. . large scale visual recognition challenge. .. . arXiv:1409.0575, 2014.. Chapter . 2: Perception (Part II). also see: neurological structures.pdf. also see: Kellogg chapter 2 (part I).. pdf. Fund. . of Cognitive . Psychology (2. nd. ) . (Kellogg). Fall . 2013. Mark Van Selst. Fei-Fei. Li and Olga Russakovsky. Refernce. to paper, photos, vision-lab, . stanford. logos. Olga . Russakovsky. ,. . Jia. . Deng, . Zhiheng. Huang, . Alex . Berg, Li . Fei. -. Fei. Detecting avocados to zucchinis: what have we done, and where are we going? ICCV 2013 . Recognition tasks. Machine learning approach: training, testing, generalization. Example classifiers. Nearest neighbor. Linear classifiers. Image features. Spatial support:. Pixel or local patch. Segmentation region. Weiqiang. . Ren. , Chong Wang, . Yanhua. Cheng, . Kaiqi. . Huang, . Tieniu. . Tan. {. wqren,cwang,yhcheng,kqhuang,tnt. }@nlpr.ia.ac.cn. Task2 : Classification + Localization. Task 2b: . Classification + localization . E . Wolf decoy for geese (plenty in New England).. Why are these decoys efficient?. Geese do not have pictures to teach their young ones what animals to avoid…. … and so they must be born with images of predators engraved in their brain. Larry Zitnick. Facebook AI Research. 1984. Neocognitron. , 1983. Recognition?. 1984. 2016. Data. GPUs. Backprop. Neocognitron. , 1983. AlexNet. , 2012. Recognition. 1984. 2016. Data. GPUs. Backprop. Recognition. Goal Two: Explain how the visual system enables us to see, and by communicating with the brain, to perceive the world.. The Visual Stimulus and the Eye. Light. . is a form of electromagnetic energy. Light travels through space in waves. The inability to recognise familiar objects presented visually is known as visual . agnosia. . There are two main types:. Apperceptive. . agnosia. – a failure to recognise due to impaired visual perception. This implies a physiological problem in the visual system.. also see: neurological structures.pdf. also see: Kellogg chapter 2 (part I).. pdf. Fund. . of Cognitive . Psychology (2. nd. ) . (Kellogg). Fall . 2013. Mark Van Selst. San Jose State University. Assignment 2: Neuroscience (5%).