CVPR 2014 Oral Talks
TechTalks from event: CVPR 2014 Oral Talks
Special 3 : Plenary Session
-
Vote ResultsLearning gave a considerable and surprising boost to computer vision, and deep neural networks appear to be the new winners of the fierce race on classification errors. Algorithm refinements are now going well beyond our understanding of the problem, and seem to make irrelevant any study of computer vision models. Yet, learning from high-dimensional data such as images, suffers from a curse of dimensionality which predicts a combinatorial explosion. Why are these neural architectures avoiding this curse? Is this rooted in properties of images and visual tasks? Can these properties be related to high-dimensional problems in other fields? We shall explore the mathematical roots of these questions, and tell a story where invariants, contractions, sparsity, dimension reduction and multiscale analysis play important roles. Images and examples will give a colorful background to the talk.
-
Plenary Talk: Are Deep Networks a Solution to Curse of Dimensionality?Learning gave a considerable and surprising boost to computer vision, and deep neural networks appear to be the new winners of the fierce race on classification errors. Algorithm refinements are now going well beyond our understanding of the problem, and seem to make irrelevant any study of computer vision models. Yet, learning from high-dimensional data such as images, suffers from a curse of dimensionality which predicts a combinatorial explosion. Why are these neural architectures avoiding this curse? Is this rooted in properties of images and visual tasks? Can these properties be related to high-dimensional problems in other fields? We shall explore the mathematical roots of these questions, and tell a story where invariants, contractions, sparsity, dimension reduction and multiscale analysis play important roles. Images and examples will give a colorful background to the talk.
- All Sessions
- Orals 1A : Matching & Reconstruction
- Orals 1B : Segmentation & Grouping
- Orals 1C : Statistical Methods & Learning I
- Orals 1D : Action Recognition
- Orals 2A : Motion & Tracking
- Orals 2B : Discrete Optimization
- Orals 2D : Attribute-Based Recognition & Human Pose Estimation
- Orals 2F : Convolutional Neural Networks
- Orals 3A : Physics-Based Vision & Shape-from-X
- Orals 3B : Video: Events, Activities & Surveillance
- Orals 3C : Medical & Biological Image Analysis
- Orals 3D : Low-Level Vision & Image Processing
- Orals 4A : Computational Photography: Sensing and Display
- Orals 4B : Recognition: Detection, Categorization, Classification
- Orals 4C : 3D Geometry & Shape
- Orals 4D : Statistical Methods and Learning II
- Orals 2E : Face & Gesture
- Orals 4E : Optimization Methods
- Orals 4F : View Synthesis & Other Applications
- Special 1 : Plenary Session
- Special 2 : Special Journal Session
- Special 3 : Plenary Session