Home

People

Research

Publications

Demos

 

 

 

 

 

News

Jobs

Prospective
Students

About

Internal


Mandar Dixit

Department of Electrical and Computer Engineering,
University of California, San Diego
9500 Gilman Drive, Mail code 0409
La Jolla, CA 92093-0409

EBU 1, Room 5512

Email: mdixit at u c s d . e d u
Phone: (858) 534-4538

 

I am currently a PhD student at the Statistical Visual Computing Lab, Department of Electrical and Computer Engineering at University of California, San Diego (UCSD). I received a B.Tech. in ECE from Visvesvaraya National Institute of Technology, Nagpur, India in May 2007 and an M.Tech. in EE from The Indian Institute of Technology, Kanpur, India in June 2009.

RESEARCH INTERESTS:

 

My research interests are computer vision and machine learning. I am currently working on developing statistical models to solve the problems of scene classification and object recognition.

PUBLICATIONS:

 

AGA: Attribute Guided Augmentation [ORAL]
M. Dixit, R. Kwitt, M. Niethammer, N. Vasconcelos
To appear at IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Honolulu, Hawaii, USA 2017

[arxiv version][ps][pdf]

 

Object based Scene Representations using Fisher Scores of Local Subspace Projections
M. Dixit, N. Vasconcelos
In Advances in Neural Information Processing Systems (NIPS)
Barcelona, Spain, 2016.

[ps][pdf][spotlight video]

 

Semantic Clustering for Robust Fine-Grained Scene Recognition
M. George, M. Dixit, G. Zogg and N. Vasconcelos
In European Conference on Computer Vision (ECCV)
Amsterdam, Netherlands, 2016.

[ps][pdf][supplement]

 

Scene Classification with Semantic Fisher Vectors
M. Dixit, S. Chen, D. Gao, N. Rasiwasia, N. Vasconcelos
In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Boston, Massachussetts, USA, 2015.

[ps][pdf][supplement]

 

Class Specific Simplex-Latent Dirichlet Allocation for Image Classification
M. Dixit*, N. Rasiwasia* and N. Vasconcelos
In Proc. IEEE International Conference on Computer Vision (ICCV)
Sydney, New South Wales, Australia, 2013.

[ps][pdf]
(*-Indicates equal contribution)

 

Adapted Gaussian Models for Image Classification
M. Dixit, N. Rasiwasia and N. Vasconcelos
In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Colorado Springs, Colorado, USA, 2011

[ps][pdf]

 

Combining Edge and Color Features for Tracking Partially Occluded Humans
M. Dixit, K.S. Venkatesh
In Proc Asian Conference on Computer Vision (ACCV), LNCS 5995, pp. 140-149
X'ian, China, Sept. 2009
[pdf]

WORKSHOPS:

Scene Classification with Semantic Fisher Vectors
Scene Understanding Workshop (SunW)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015, Boston, MA.

[SunW]

Contextual CNN for Scene Classification
Large Scale Scene Understanding (LSUN) Workshop at
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015, Boston, MA.

[LSUN 2015 leaderboard]

TALKS:

Knowledge Transfer with Deep Neural Networks
Microsoft AI & Research, May 2017

A Semantic Representation for Scene Classification
Intel Inc., Oct 2015

Scene Classification with Convolutional Neural Networks
Qualcomm Inc., May 2015

Scene Classification with Semantic Fisher Vectors
Samsung, Dec 2014

AWARDS:

Graduate Fellowship, UCSD, 2009-2010

Rajiv Gandhi Talent Fellowship, Jawaharlal Nehru Center for Advanced Scientific Research (JNCASR), 2006

NIPS Travel Award 2016

ICCV Travel Award 2013

SERVICE:

Reviewer, Neural Information Processing Systems (NIPS) 2017

Reviewer, IEEE International Conf. on Computer Vision (ICCV) 2017

Reviewer, European Conf. on Computer Vision (ECCV) 2016

Reviewer, IEEE Computer Vision and Pattern Recognition (CVPR) 2016, 2017

Technical Program Committee, International Conf. Multimedia Retrieval (ICMR) 2015

Student member, IEEE, Computer Vision Foundation (CvF)


Last update: 08/12/2016

 



Copyright @ 2016 www.svcl.ucsd.edu