• Publications
  • Influence
Label Consistent K-SVD: Learning a Discriminative Dictionary for Recognition
A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding and introduces a new label consistency constraint called "discriminative sparse-code error" to enforce discriminability in sparse codes during the dictionary learning process. Expand
Non-parametric Model for Background Subtraction
A novel non-parametric background model that can handle situations where the background of the scene is cluttered and not completely static but contains small motions such as tree branches and bushes is presented. Expand
Real-time foreground-background segmentation using codebook model
A real-time algorithm for foreground-background segmentation that can handle scenes containing moving backgrounds or illumination variations, and it achieves robust detection for different types of videos is presented. Expand
Soft-NMS — Improving Object Detection with One Line of Code
Soft-NMS is proposed, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M and improves state-of-the-art in object detection from 39.8% to 40.9% with a single model. Expand
W4: Real-Time Surveillance of People and Their Activities
W/sup 4/ employs a combination of shape analysis and tracking to locate people and their parts and to create models of people's appearance so that they can be tracked through interactions such as occlusions. Expand
Learning a discriminative dictionary for sparse coding via label consistent K-SVD
A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding is presented, which learns a single over-complete dictionary and an optimal linear classifier jointly and yields dictionaries so that feature points with the same class labels have similar sparse codes. Expand
Learning Temporal Regularity in Video Sequences
This work proposes two methods that are built upon the autoencoders for their ability to work with little to no supervision, and builds a fully convolutional feed-forward autoencoder to learn both the local features and the classifiers as an end-to-end learning framework. Expand
Model-based object pose in 25 lines of code
  • D. DeMenthon, L. Davis
  • Mathematics, Computer Science
  • International Journal of Computer Vision
  • 1 June 1995
Compared to classic approaches making use of Newton's method, POSIT does not require starting from an initial guess, and computes the pose using an order of magnitude fewer floating point operations; it may therefore be a useful alternative for real-time operation. Expand
Covariance discriminative learning: A natural and efficient approach to image set classification
A novel discriminative learning approach to image set classification by modeling the image set with its natural second-order statistic, i.e. covariance matrix, which shows the superiority of this method over state-of-the-art ones in both accuracy and efficiency, but also its stability to two real challenges: noisy set data and varying set size. Expand
An assessment of support vector machines for land cover classification
An introduction to the theoretical development of the SVM and an experimental evaluation of its accuracy, stability and training speed in deriving land cover classifications from satellite images are given. Expand