• Publications
  • Influence
A New Baseline for Image Annotation
TLDR
We introduce a new baseline technique for image annotation that treats annotation as a retrieval problem. Expand
  • 460
  • 92
  • PDF
Face tracking and recognition with visual constraints in real-world videos
TLDR
We address the problem of tracking and recognizing faces in real-world, noisy videos using a tracker that adaptively builds a target model reflecting changes in appearance, typical of a video setting. Expand
  • 447
  • 75
  • PDF
Visual Interpretation of Hand Gestures for Human-Computer Interaction: A Review
TLDR
In a process for preparing phosphoric acid by contact of sulphuric acid and phosphate rock with filtration of the gypsum slurry and recycle of the rest for contact with fresh rock, a fraction of the recycle slurry is treated with calcium sulphate hemihydrate and the slurry comprising hemihYDrate is returned to contact the mixture of phosphate rock. Expand
  • 1,873
  • 62
  • PDF
Baselines for Image Annotation
TLDR
In this work, we introduce a new and simple baseline technique for image annotation that treats annotation as a retrieval problem. Expand
  • 192
  • 42
  • PDF
Learning Switching Linear Models of Human Motion
TLDR
We present results for human motion synthesis, classification, and visual tracking using learned SLDS models. Expand
  • 336
  • 20
  • PDF
Toward multimodal human-computer interface
TLDR
We consider some of the emerging novel input modalities for HCI and the fundamental issues in integrating them at various levels, from early signal level to intermediate feature level. Expand
  • 319
  • 19
Discovering clusters in motion time-series data
An approach is proposed for clustering time-series data. The approach can be used to discover groupings of similar object motions that were observed in a video collection. A finite mixture of hiddenExpand
  • 206
  • 17
  • PDF
RankGene: identification of diagnostic genes based on expression data
TLDR
RankGene is a program for analyzing gene expression data and computing diagnostic genes based on their predictive power in distinguishing between different types of samples. Expand
  • 201
  • 15
  • PDF
A dynamic Bayesian network approach to figure tracking using learned dynamic models
TLDR
This paper describes a novel DBN-based switching linear dynamic system (SLDS) model and presents its application to figure motion analysis. Expand
  • 288
  • 14
  • PDF
Deep Structured Learning for Facial Action Unit Intensity Estimation
TLDR
We propose a novel Copula CNN deep learning approach for modeling multivariate ordinal variables and estimate complex feature representations simultaneously by combining conditional random field encoded AU dependencies with deep learning. Expand
  • 47
  • 11
  • PDF