Understanding visual scenes in 200 msec: Results from Human and Modeling Experiments 

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=YClUTvHN5nA


Duration: 1:11:03
113 views
0

One of the remarkable aspects of human image understanding is that we are able to recognize the meaning of a novel image very quickly and independently of the complexity of the image. This talk will review findings in human perception that help us understand which mechanisms the human brain uses to achieve fast visual recognition, accurate visual search and adequate memorization of visual information. It also will describe the limits of human perception, as well as how to use our understanding of the pros and cons of these mechanisms for designing artificial vision systems and visual displays for human use.



Other Videos By Microsoft Research


2016-09-07Enhanced MVDR beamforming for Arrays of Directional Microphones
2016-09-07When Separation Logic met Java
2016-09-07Microphone Array for Audience Capture in Lecture Rooms
2016-09-07Learning to Label Images
2016-09-07On the Compressibility of NP Instances and Cryptographic Applications
2016-09-07Search: Use of Relevance Feedback and Estimating Effectiveness of Searches
2016-09-07Tool Support for Proof Engineering
2016-09-07Attack-Resistant Algorithms for Massive Networks
2016-09-07Lambda Legal: Making the Case for Equality
2016-09-07Introducing Nielsen Buzzmetrics Research The Global Measurement Standard in Consumer Generated Media
2016-09-07Understanding visual scenes in 200 msec: Results from Human and Modeling Experiments 
2016-09-07Exploiting Multiple Cores Today: Scalability and Reliability For Off-the-shelf Software
2016-09-07Proof Procedures for Separated Heap Abstractions
2016-09-07Client-Side Echo Cancellation for Multi-Party Audio Conferencing
2016-09-07Variance analyses from invariance analyses
2016-09-07Modelling the performance of wireless networks employing the IEEE 802.11 MAC
2016-09-07Geometric Optics, Duality and Congestion in Sensornets [1/2]
2016-09-07All Rise: Somebodies, Nobodies and the Politics of Dignity
2016-09-07Hierarchical Bayesian Models for Rating Individual Players from Group Competitions
2016-09-07Interoperability and natural language processing for business rules engines
2016-09-07Random Matrices and Spectral Clustering Abstract


Tags:
microsoft research