• Publications
  • Influence
Generalized Zero-Shot Recognition Based on Visually Semantic Embedding
TLDR
We propose a novel Generalized Zero-Shot learning (GZSL) method that is agnostic to both unseen images and unseen semantic vectors during training. Expand
  • 41
  • 6
  • PDF
Zero Shot Detection
TLDR
We propose a novel zero-shot method based on training an end-to-end model that fuses semantic attribute prediction with visual features to propose object bounding boxes for seen and unseen classes. Expand
  • 41
  • 5
  • PDF
Don’t Even Look Once: Synthesizing Features for Zero-Shot Detection
TLDR
We propose a novel detection algorithm “Don’t Even Look Once (DELO),” that synthesizes visual features for unseen objects and augments existing training algorithms to incorporate unseen object detection. Expand
  • 10
  • 1
  • PDF
Cost aware Inference for IoT Devices
TLDR
We introduce a novel distributed inference problem for energy-limited IoT devices, which offer exciting applications for machine learning. Expand
  • 8
  • PDF
Learning Classifiers for Target Domain with Limited or No Labels
TLDR
We propose a novel visual attribute encoding method that encodes each image as a low-dimensional probability vector composed of prototypical part-type probabilities. Expand
  • 2
  • PDF
Learning for New Visual Environments with Limited Labels
TLDR
We propose a novel visual attribute encoding method that encodes each image as a low-dimensional probability vector composed of prototypical part-type probabilities. Expand
  • 1
Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts.
TLDR
We propose a novel visual attribute encoding method that encodes each image as a low-dimensional probability vector composed of prototypical part-type probabilities. Expand
  • 1