N
Neeraj Kumar
Researcher at Thapar University
Publications - 335
Citations - 10279
Neeraj Kumar is an academic researcher from Thapar University. The author has contributed to research in topics: Computer science & The Internet. The author has an hindex of 33, co-authored 237 publications receiving 7639 citations. Previous affiliations of Neeraj Kumar include University of Groningen & Pacific Northwest National Laboratory.
Papers
More filters
Proceedings ArticleDOI
Attribute and simile classifiers for face verification
TL;DR: Two novel methods for face verification using binary classifiers trained to recognize the presence or absence of describable aspects of visual appearance and a new data set of real-world images of public figures acquired from the internet.
Book ChapterDOI
Leafsnap: a computer vision system for automatic plant species identification
Neeraj Kumar,Peter N. Belhumeur,Arijit Biswas,David W. Jacobs,W. John Kress,Ida C. Lopez,João V. B. Soares +6 more
TL;DR: The first mobile app for identifying plant species using automatic visual recognition from photographs of their leaves is described, which obtains state-of-the-art performance on the real-world images from the new Leafsnap Dataset --- the largest of its kind.
Journal ArticleDOI
Localizing Parts of Faces Using a Consensus of Exemplars
TL;DR: This work presents a novel approach to localizing parts in images of human faces that combines the output of local detectors with a nonparametric set of global models for the part locations based on over 1,000 hand-labeled exemplar images and derives a Bayesian objective function.
Proceedings ArticleDOI
Localizing parts of faces using a consensus of exemplars
TL;DR: A novel approach to localizing parts in images of human faces that combines the output of local detectors with a non-parametric set of global models for the part locations based on over one thousand hand-labeled exemplar images and derives a Bayesian objective function.
Journal ArticleDOI
Describable Visual Attributes for Face Verification and Image Search
TL;DR: It is shown how one can create and label large data sets of real-world images to train classifiers which measure the presence, absence, or degree to which an attribute is expressed in images, which can then automatically label new images.