• Publications
  • Influence
A New Baseline for Image Annotation
TLDR
This work introduces a new baseline technique for image annotation that treats annotation as a retrieval problem and outperforms the current state-of-the-art methods on two standard and one large Web dataset. Expand
Face tracking and recognition with visual constraints in real-world videos
TLDR
This work addresses 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 and introduces visual constraints using a combination of generative and discriminative models in a particle filtering framework. Expand
Visual Interpretation of Hand Gestures for Human-Computer Interaction: A Review
TLDR
A fraction of the recycle slurry is treated with sulphuric acid to convert at least some of the gypsum to calcium sulphate hemihydrate and the slurry comprising hemihYDrate is returned to contact the mixture of phosphate rock, phosphoric acid and recycle Gypsum slurry. Expand
Baselines for Image Annotation
TLDR
This work introduces a new and simple baseline technique for image annotation that treats annotation as a retrieval problem and outperforms the current state-of-the-art methods on two standard and one large Web dataset. Expand
Learning Switching Linear Models of Human Motion
TLDR
A new variational inference algorithm is obtained by casting the SLDS model as a Dynamic Bayesian Network, and classification experiments show the superiority of SLDS over conventional HMM's for the problem domain. Expand
Toward multimodal human-computer interface
TLDR
It is clear that further research is needed for interpreting and fitting multiple sensing modalities in the context of HCI and the fundamental issues in integrating them at various levels, from early signal level to intermediate feature level to late decision level. Expand
Discovering clusters in motion time-series data
TLDR
An approach is proposed for clustering time-series data that allows each sequence to belong to more than a single HMM with some probability, and the hard decision about the sequence class membership can be deferred until a later time when such a decision is required. Expand
Deep Structured Learning for Facial Action Unit Intensity Estimation
TLDR
A novel Copula CNN deep learning approach for modeling multivariate ordinal variables and their non-linear dependencies via copula functions modeled as cliques of a CRF that is jointly optimized with deep CNN feature encoding layers using a newly introduced balanced batch iterative training algorithm. Expand
A dynamic Bayesian network approach to figure tracking using learned dynamic models
TLDR
A novel DBN-based switching linear dynamic system (SLDS) model that is an approximate Viterbi inference technique for overcoming the intractability of exact inference in mixed-state DBNs is described and its application to figure motion analysis is presented. Expand
Scalable Algorithms for String Kernels with Inexact Matching
TLDR
A new family of linear time algorithms for string comparison with mismatches under the string kernels framework that improves theoretical complexity bounds of existing approaches while scaling well in sequence alphabet size, the number of allowed mismatches and the size of the dataset. Expand
...
1
2
3
4
5
...