Deva Ramanan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Deva Ramanan has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Charless C. Fowlkes
University of California
3 shared publications - Carl Vondrick
MIT MIT MIT
1 shared publication - Carl Vondrick1 shared publication
- Chaitanya Desai
Department of Computer Science, UC Irvine, Irvine, USA
1 shared publication - Donald J. Patterson
University of California
1 shared publication - Gregory Rogez
Dept of Computer Science University of California Irvine CA USA
1 shared publication
Latest Publications
- 19 March 2015
- Published by Springer Nature
- p. 356-371
3D Hand Pose Detection in Egocentric RGB-D Images
- 19 March 2015
- Published by Springer Nature
- p. 356-371
3D Hand Pose Detection in Egocentric RGB-D Images
- Top Cited Papers
- 12 March 2015
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 119 (1) , 76-92
Do We Need More Training Data?
- 12 March 2015
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 119 (1) , 76-92
Top Cited PapersDo We Need More Training Data?
- Open Access
Egocentric Pose Recognition in Four Lines of Code
We tackle the problem of estimating the 3D pose of an individual's upper limbs (arms+hands) from a chest mounted depth-camera. Importantly, we consider pose estimation during everyday interactions with objects. Past work shows that strong pose+viewpoint priors and depth-based features are crucial for robust performance. In egocentric views, hands and arms are observable within a well defined volume in front of the camera. We call this volume an egocentric workspace. A notable property is that hand appearance correlates with workspace location. To exploit this correlation, we classify arm+hand configurations in a global egocentric coordinate frame, rather than a local scanning window. This greatly simplify the architecture and improves performance. We propose an efficient pipeline which 1) generates synthetic workspace exemplars for training using a virtual chest-mounted camera whose intrinsic parameters match our physical camera, 2) computes perspective-aware depth features on this entire volume and 3) recognizes discrete arm+hand pose classes through a sparse multi-class SVM. Our method provides state-of-the-art hand pose recognition performance from egocentric RGB-D images in real-time.
Open AccessEgocentric Pose Recognition in Four Lines of Code
We tackle the problem of estimating the 3D pose of an individual's upper limbs (arms+hands) from a chest mounted depth-camera. Importantly, we consider pose estimation during everyday interactions with objects. Past work shows that strong pose+viewpoint priors and depth-based features are crucial for robust performance. In egocentric views, hands and arms are observable within a well defined volume in front of the camera. We call this volume an egocentric workspace. A notable property is that hand appearance correlates with workspace location. To exploit this correlation, we classify arm+hand configurations in a global egocentric coordinate frame, rather than a local scanning window. This greatly simplify the architecture and improves performance. We propose an efficient pipeline which 1) generates synthetic workspace exemplars for training using a virtual chest-mounted camera whose intrinsic parameters match our physical camera, 2) computes perspective-aware depth features on this entire volume and 3) recognizes discrete arm+hand pose classes through a sparse multi-class SVM. Our method provides state-of-the-art hand pose recognition performance from egocentric RGB-D images in real-time.
- Top Cited Papers
- 5 September 2012
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 101 (1) , 184-204
Efficiently Scaling up Crowdsourced Video Annotation
- 5 September 2012
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 101 (1) , 184-204
Top Cited PapersEfficiently Scaling up Crowdsourced Video Annotation
- 13 October 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 34 (9) , 1731-1743
Layered Object Models for Image Segmentation
We formulate a layered model for object detection and image segmentation. We describe a generative probabilistic model that composites the output of a bank of object detectors in order to define shape masks and explain the appearance, depth ordering, and labels of all pixels in an image. Notably, our system estimates both class labels and object instance labels. Building on previous benchmark criteria for object detection and image segmentation, we define a novel score that evaluates both class and instance segmentation. We evaluate our system on the PASCAL 2009 and 2010 segmentation challenge data sets and show good test results with state-of-the-art performance in several categories, including segmenting humans.
- 13 October 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 34 (9) , 1731-1743
Layered Object Models for Image Segmentation
We formulate a layered model for object detection and image segmentation. We describe a generative probabilistic model that composites the output of a bank of object detectors in order to define shape masks and explain the appearance, depth ordering, and labels of all pixels in an image. Notably, our system estimates both class labels and object instance labels. Building on previous benchmark criteria for object detection and image segmentation, we define a novel score that evaluates both class and instance segmentation. We evaluate our system on the PASCAL 2009 and 2010 segmentation challenge data sets and show good test results with state-of-the-art performance in several categories, including segmenting humans.
- 2 April 2011
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 95 (1) , 1-12
Discriminative Models for Multi-Class Object Layout
- 2 April 2011
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 95 (1) , 1-12
Discriminative Models for Multi-Class Object Layout
- 1 January 2011
- Published by Springer Nature
- p. 199-223
Part-Based Models for Finding People and Estimating Their Pose
- 1 January 2011
- Published by Springer Nature
- p. 199-223
Part-Based Models for Finding People and Estimating Their Pose
- 1 July 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 33 (4) , 794-806
Local Distance Functions: A Taxonomy, New Algorithms, and an Evaluation
We present a taxonomy for local distance functions where most existing algorithms can be regarded as approximations of the geodesic distance defined by a metric tensor. We categorize existing algorithms by how, where, and when they estimate the metric tensor. We also extend the taxonomy along each axis. How: We introduce hybrid algorithms that use a combination of techniques to ameliorate overfitting. Where: We present an exact polynomial-time algorithm to integrate the metric tensor along the lines between the test and training points under the assumption that the metric tensor is piecewise constant. When: We propose an interpolation algorithm where the metric tensor is sampled at a number of references points during the offline phase. The reference points are then interpolated during the online classification phase. We also present a comprehensive evaluation on tasks in face recognition, object recognition, and digit recognition.
- 1 July 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 33 (4) , 794-806
Local Distance Functions: A Taxonomy, New Algorithms, and an Evaluation
We present a taxonomy for local distance functions where most existing algorithms can be regarded as approximations of the geodesic distance defined by a metric tensor. We categorize existing algorithms by how, where, and when they estimate the metric tensor. We also extend the taxonomy along each axis. How: We introduce hybrid algorithms that use a combination of techniques to ameliorate overfitting. Where: We present an exact polynomial-time algorithm to integrate the metric tensor along the lines between the test and training points under the assumption that the metric tensor is piecewise constant. When: We propose an interpolation algorithm where the metric tensor is sampled at a number of references points during the offline phase. The reference points are then interpolated during the online classification phase. We also present a comprehensive evaluation on tasks in face recognition, object recognition, and digit recognition.
- 12 February 2010
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 5 (4) , 215-230
SEMARTCam scheduler: semantics driven real-time data collection from indoor camera networks to maximize event detection
- 12 February 2010
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 5 (4) , 215-230
SEMARTCam scheduler: semantics driven real-time data collection from indoor camera networks to maximize event detection