Pietro Perona

Also published under:P. Perona

Affiliation

California Institute of Technology
AWS

Topic

Behavioral Analysis,Bounding Box,Convolutional Neural Network,Mean Average Precision,Appearance Features,Behavior Classification,Behavioral Video,Bidirectional Long Short-term Memory,Computer Vision,Contrastive Loss,Data Augmentation,Face Images,Image Texture,Interesting Behavior,Manual Annotation,Object Detection,Optical Character Recognition,Pose Estimation,Reconstruction Loss,Recurrent Neural Network,Representation Learning,Self-supervised Learning,Spatiotemporal Differences,Structural Similarity Index Measure,Training Data,Training Set,2D Keypoints,2D Pose,3D Coordinates,3D Keypoints,3D Method,3D Movement,3D Pose,Access Control,Action Detection,Algorithmic Bias,Ambiguity,Annotated Transcripts,Annotation Data,Attention Mechanism,Augmentation Procedures,Automatic System,Background Noise,Behavior Properties,Benchmark,Benchmark Datasets,Beta Distribution,Binary Cross Entropy,Binary Cross-entropy Loss,Black Females,

Biography

Pietro Perona graduated in electrical engineering from the Università di Padova in 1985 and received the PhD degree in electrical engineering and computer science from the University of California, Berkeley, in 1990. After a postdoctoral fellowship at MIT in 1990-1991 he joined the faculty of the California Institute of Technology in 1991, where is now the Allen E. Puckett Professor of Electrical Engineering and Computation and Neural Systems. His current interests are visual recognition, modeling and measuring animal behavior, and Visipedia. He has worked on anisotropic diffusion, multiresolution-multi-orientation filtering, human texture perception and segmentation, dynamic vision, grouping, analysis of human motion, recognition of object categories, and modeling visual search.