• Publications
  • Influence
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
Background and foreground modeling using nonparametric kernel density estimation for visual surveillance
This paper constructs a statistical representation of the scene background that supports sensitive detection of moving objects in the scene, but is robust to clutter arising out of natural scene variations. Expand
A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts
This work proposes a simple yet effective generative model that takes as input noisy text descriptions about an unseen class and generates synthesized visual features for this class and shows that this method consistently outperforms the state of the art on the largest available benchmarks on Text-based Zero-shot Learning. Expand
Inferring 3D body pose from silhouettes using activity manifold learning
We aim to infer 3D body pose directly from human silhouettes. Given a visual input (silhouette), the objective is to recover the intrinsic body configuration, recover the viewpoint, reconstruct theExpand
SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition
A new CNN architecture that integrates semantic part detection and abstraction (SPDACNN) for fine-grained classification by providing an end-to-end network that performs detection, localization of multiple semantic parts, and whole object recognition within one framework that shares the computation of convolutional filters. Expand
Graphical Contrastive Losses for Scene Graph Parsing
A set of contrastive loss formulations are proposed that specifically target these types of errors within the scene graph parsing problem, collectively termed the Graphical Contrastive Losses, and show improved results over the best previous methods on the Visual Genome and Visual Relationship Detection datasets. Expand
Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions
An approach for zero-shot learning of object categories where the description of unseen categories comes in the form of typical text such as an encyclopedia entry, without the need to explicitly defined attributes is proposed. Expand
Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature
A machine is developed that is able to make aesthetic-related semantic-level judgments, such as predicting a painting's style, genre, and artist, as well as providing similarity measures optimized based on the knowledge available in the domain of art historical interpretation. Expand
Large-Scale Visual Relationship Understanding
A new relationship detection model is developed that embeds objects and relations into two vector spaces where both discriminative capability and semantic affinity are preserved and can achieve superior performance even when the visual entity categories scale up to more than 80,000, with extremely skewed class distribution. Expand
Genetic Identification