CSAIL
* *Massachusetts Institute of Technology, AI Lab
* Accurate and Scalable Surface Representation and Reconstruction from Images
* Approximate Correspondences in High Dimensions
* Automated Audio-visual Activity Analysis
* Boosting a Biologically Inspired Local Descriptor for Geometry-free Face and Full Multi-view 3D Object Recognition
* Combining Object and Feature Dynamics in Probabilistic Tracking
* Combining Variable Selection with Dimensionality Reduction
* Comparing Visual Features for Morphing Based Recognition
* Context-based Visual Feedback Recognition
* De-Emphasis of Distracting Image Regions Using Texture Power Maps
* Detecting and tracking multiple interacting objects without class-specific models
* Expectation Maximization Approach for Integrated Registration, Segmentation, and Intensity Correction, An
* Fast Approximation of the Bilateral Filter Using a Signal Processing Approach, A
* LabelMe: A Database and Web-Based Tool for Image Annotation
* Learning a Dictionary of Shape-Components in Visual Cortex: Comparison with Neurons, Humans and Machines
* Learning Semantic Scene Models by Trajectory Analysis
* Nonlinear Latent Variable Models for Video Sequences
* Novel Active Contour Framework. Multi-component Level Set Evolution under Topology Control, A
* Pyramid Match Kernel: Discriminative Classification with Sets of Image Features, The
* Pyramid Match Kernel: Discriminative Classification with Sets of Image Features, The
* Random Lens Imaging
* Receptive field structures for recognition
* Simultaneous Localization, Calibration, and Tracking in an ad Hoc Sensor Network
* Team MIT Urban Challenge Technical Report
* Tiny images
* Using computational models to study texture representations in the human visual system
* Wide-Area Egomotion Estimation from Known 3D Structure
27 for CSAIL