Balakrishnan Varadarajan
Balakrishnan Varadarajan
Software Engineer, Google Research
Verified email at
Cited by
Cited by
Youtube-8m: A large-scale video classification benchmark
S Abu-El-Haija, N Kothari, J Lee, P Natsev, G Toderici, B Varadarajan, ...
arXiv preprint arXiv:1609.08675, 2016
Combining active learning and semi-supervised learning using gaussian fields and harmonic functions
X Zhu, J Lafferty, Z Ghahramani
ICML 2003 workshop on the continuum from labeled to unlabeled data in …, 2003
Green function estimates and Harnack inequality for subordinate Brownian motions
M Rao, R Song, Z Vondraček
Potential Analysis 25 (1), 1-27, 2006
Jhu-isi gesture and skill assessment working set (jigsaws): A surgical activity dataset for human motion modeling
Y Gao, SS Vedula, CE Reiley, N Ahmidi, B Varadarajan, HC Lin, L Tao, ...
MICCAI workshop: M2cai 3, 3, 2014
Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maximization criterion
D Yu, B Varadarajan, L Deng, A Acero
Computer Speech & Language 24 (3), 433-444, 2010
Unsupervised learning of acoustic sub-word units
B Varadarajan, S Khudanpur, E Dupoux
Proceedings of ACL-08: HLT, Short Papers, 165-168, 2008
Data-derived models for segmentation with application to surgical assessment and training
B Varadarajan, C Reiley, H Lin, S Khudanpur, G Hager
International Conference on Medical Image Computing and Computer-Assisted …, 2009
A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition
A Jansen, E Dupoux, S Goldwater, M Johnson, S Khudanpur, K Church, ...
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
Automatic recognition of surgical motions using statistical modeling for capturing variability
CE Reiley, HC Lin, B Varadarajan, B Vagvolgyi, S Khudanpur, DD Yuh, ...
MMVR 132, 396-401, 2008
Universal background model based speech recognition
D Povey, SM Chu, B Varadarajan
2008 IEEE International Conference on Acoustics, Speech and Signal …, 2008
Stepwise optimal subspace pursuit for improving sparse recovery
B Varadarajan, S Khudanpur, TD Tran
IEEE Signal Processing Letters 18 (1), 27-30, 2010
Collaborative deep metric learning for video understanding
J Lee, S Abu-El-Haija, B Varadarajan, A Natsev
Proceedings of the 24th ACM SIGKDD International Conference on Knowledge …, 2018
Selecting and presenting representative frames for video previews
S Shetty, T Izo, MH Tsai, S Vijayanarasimhan, A Natsev, S Abu-El-Haija, ...
US Patent 9,953,222, 2018
Learning and inference algorithms for dynamical system models of dextrous motion
B Varadarajan
The Johns Hopkins University, 2011
Tnt: Target-driven trajectory prediction
H Zhao, J Gao, T Lan, C Sun, B Sapp, B Varadarajan, Y Shen, Y Shen, ...
arXiv preprint arXiv:2008.08294, 2020
Efficient large scale video classification
B Varadarajan, G Toderici, S Vijayanarasimhan, A Natsev
arXiv preprint arXiv:1505.06250, 2015
Maximizing global entropy reduction for active learning in speech recognition
B Varadarajan, D Yu, L Deng, A Acero
2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009
Quick fmllr for speaker adaptation in speech recognition
B Varadarajan, D Povey, SM Chu
2008 IEEE International Conference on Acoustics, Speech and Signal …, 2008
Automatically learning speaker-independent acoustic subword units
B Varadarajan, S Khudanpur
Ninth Annual Conference of the International Speech Communication Association, 2008
Exploring the relative role of bottom-up and top-down information in phoneme learning
A Fourtassi, T Schatz, B Varadarajan, E Dupoux
Proceedings of the 52nd Annual Meeting of the Association for Computational …, 2014
The system can't perform the operation now. Try again later.
Articles 1–20