David Demirdjian - Academia.edu (original) (raw)

Uploads

Papers by David Demirdjian

Research paper thumbnail of Multi-signal gesture recognition using temporal smoothing hidden conditional random fields

Research paper thumbnail of Recognizing events with temporal random forests

In this paper, we present a novel technique for classifying multimodal temporal events. Our main ... more In this paper, we present a novel technique for classifying multimodal temporal events. Our main contribution is the introduction of temporal random forests (TRFs), an extension of random forests (and decision trees in general) to the time domain. The approach is relatively simple and able to discriminatively learn event classes while performing feature selection in an implicit fashion. We describe here our ongoing research and present experiments performed on gesture and audio-visual speech recognition datasets comparing our method against state-of-the-art algorithms.

Research paper thumbnail of Untethered gesture acquisition and recognition for virtual world manipulation

Virtual Reality, Jul 12, 2005

Research paper thumbnail of Tracking body and hands for gesture recognition: NATOPS aircraft handling signals database

Research paper thumbnail of Markerless motion capture techniques to facilitate rehabilitation intervention

Research paper thumbnail of Detecting communication errors from visual cues during the system's conversational turn

Research paper thumbnail of Gesture + Play Exploring Full-Body Navigation for Virtual Environments

Research paper thumbnail of Inferring body pose using speech content

Research paper thumbnail of Combining Geometric- and View-Based Approaches for Articulated Pose Estimation

Lecture Notes in Computer Science, 2004

Research paper thumbnail of Distributed pointing for multimodal collaboration over sketched diagrams

Research paper thumbnail of Enforcing Constraints for Human Body Tracking

Research paper thumbnail of Conditional Random People: Tracking Humans with CRFs and Grid Filters

Research paper thumbnail of Patch-Based Pose Inference with a Mixture of Density Estimators

Springer eBooks, Nov 3, 2007

This paper presents a patch-based approach for pose estimation from single images using a kerneli... more This paper presents a patch-based approach for pose estimation from single images using a kernelized density voting scheme. We introduce a boosting-like algorithm that models the density using a mixture of weighted ‘weak’ estimators. The ‘weak’ density estimators and corresponding weights are learned iteratively from a training set, providing an efficient method for feature selection. Given a query image, voting

Research paper thumbnail of Recognition of temporal events using multiscale bags of features

This paper presents a novel method for learning classes of temporal sequences using a bag-of-feat... more This paper presents a novel method for learning classes of temporal sequences using a bag-of-features approach. We define a temporal sequence as a bag of temporal features and show how this representation can be used for the recognition and segmentation of temporal events. A codebook of temporal descriptors, representing the local temporal texture, is automatically constructed from a set of

Research paper thumbnail of Untethered gesture acquisition and recognition for a multimodal conversational system

Research paper thumbnail of Gesture + play

Navigating virtual environments usually requires a wired interface, game console, or keyboard. Th... more Navigating virtual environments usually requires a wired interface, game console, or keyboard. The advent of perceptual interface techniques allows a new option, the passive and untethered sensing of users' pose and gesture to allow them maneuver through virtual worlds. We show new algorithms for passive, real-time articulated tracking with standard cameras and personal computers. Several different interaction styles are compared,

Research paper thumbnail of Motion estimation from disparity images

Research paper thumbnail of Le mouvement projectif : théorie et applications pour l'autocalibrage et la segmentation du mouvement

Research paper thumbnail of Session details: Multimodal devices and sensors (Oral)

Research paper thumbnail of Navigating in virtual environments using a vision-based interface

... Science and Artificial Intilligens, MIT 200 Technology Square, Cambridge, MA 20139, USA konra... more ... Science and Artificial Intilligens, MIT 200 Technology Square, Cambridge, MA 20139, USA konrad@csail.mit.edu, demirdji@csail.mit.edu, trevor@csail.mit ... First we performed a Wizard ofOZ (WOz) study with the major aim of gathering qualitative data like: what gestures are most ...

Research paper thumbnail of Multi-signal gesture recognition using temporal smoothing hidden conditional random fields

Research paper thumbnail of Recognizing events with temporal random forests

In this paper, we present a novel technique for classifying multimodal temporal events. Our main ... more In this paper, we present a novel technique for classifying multimodal temporal events. Our main contribution is the introduction of temporal random forests (TRFs), an extension of random forests (and decision trees in general) to the time domain. The approach is relatively simple and able to discriminatively learn event classes while performing feature selection in an implicit fashion. We describe here our ongoing research and present experiments performed on gesture and audio-visual speech recognition datasets comparing our method against state-of-the-art algorithms.

Research paper thumbnail of Untethered gesture acquisition and recognition for virtual world manipulation

Virtual Reality, Jul 12, 2005

Research paper thumbnail of Tracking body and hands for gesture recognition: NATOPS aircraft handling signals database

Research paper thumbnail of Markerless motion capture techniques to facilitate rehabilitation intervention

Research paper thumbnail of Detecting communication errors from visual cues during the system's conversational turn

Research paper thumbnail of Gesture + Play Exploring Full-Body Navigation for Virtual Environments

Research paper thumbnail of Inferring body pose using speech content

Research paper thumbnail of Combining Geometric- and View-Based Approaches for Articulated Pose Estimation

Lecture Notes in Computer Science, 2004

Research paper thumbnail of Distributed pointing for multimodal collaboration over sketched diagrams

Research paper thumbnail of Enforcing Constraints for Human Body Tracking

Research paper thumbnail of Conditional Random People: Tracking Humans with CRFs and Grid Filters

Research paper thumbnail of Patch-Based Pose Inference with a Mixture of Density Estimators

Springer eBooks, Nov 3, 2007

This paper presents a patch-based approach for pose estimation from single images using a kerneli... more This paper presents a patch-based approach for pose estimation from single images using a kernelized density voting scheme. We introduce a boosting-like algorithm that models the density using a mixture of weighted ‘weak’ estimators. The ‘weak’ density estimators and corresponding weights are learned iteratively from a training set, providing an efficient method for feature selection. Given a query image, voting

Research paper thumbnail of Recognition of temporal events using multiscale bags of features

This paper presents a novel method for learning classes of temporal sequences using a bag-of-feat... more This paper presents a novel method for learning classes of temporal sequences using a bag-of-features approach. We define a temporal sequence as a bag of temporal features and show how this representation can be used for the recognition and segmentation of temporal events. A codebook of temporal descriptors, representing the local temporal texture, is automatically constructed from a set of

Research paper thumbnail of Untethered gesture acquisition and recognition for a multimodal conversational system

Research paper thumbnail of Gesture + play

Navigating virtual environments usually requires a wired interface, game console, or keyboard. Th... more Navigating virtual environments usually requires a wired interface, game console, or keyboard. The advent of perceptual interface techniques allows a new option, the passive and untethered sensing of users' pose and gesture to allow them maneuver through virtual worlds. We show new algorithms for passive, real-time articulated tracking with standard cameras and personal computers. Several different interaction styles are compared,

Research paper thumbnail of Motion estimation from disparity images

Research paper thumbnail of Le mouvement projectif : théorie et applications pour l'autocalibrage et la segmentation du mouvement

Research paper thumbnail of Session details: Multimodal devices and sensors (Oral)

Research paper thumbnail of Navigating in virtual environments using a vision-based interface

... Science and Artificial Intilligens, MIT 200 Technology Square, Cambridge, MA 20139, USA konra... more ... Science and Artificial Intilligens, MIT 200 Technology Square, Cambridge, MA 20139, USA konrad@csail.mit.edu, demirdji@csail.mit.edu, trevor@csail.mit ... First we performed a Wizard ofOZ (WOz) study with the major aim of gathering qualitative data like: what gestures are most ...

Log In