Follow
Varsha Hedau
Varsha Hedau
Tech Lead, Sr Applied Scientist, Amazon Lab126
No verified email - Homepage
Title
Cited by
Cited by
Year
Recovering the spatial layout of cluttered rooms
V Hedau, D Hoiem, D Forsyth
2009 IEEE 12th international conference on computer vision, 1849-1856, 2009
6682009
Rendering synthetic objects into legacy photographs
K Karsch, V Hedau, D Forsyth, D Hoiem
ACM Transactions on graphics (TOG) 30 (6), 1-12, 2011
3872011
Thinking inside the box: Using appearance models and context based on room geometry
V Hedau, D Hoiem, D Forsyth
Computer Vision–ECCV 2010: 11th European Conference on Computer Vision …, 2010
3532010
Recovering free space of indoor scenes from a single image
V Hedau, D Hoiem, D Forsyth
2012 IEEE conference on computer vision and pattern recognition, 2807-2814, 2012
1592012
Fashionvlp: Vision language transformer for fashion retrieval with feedback
S Goenka, Z Zheng, A Jaiswal, R Chada, Y Wu, V Hedau, P Natarajan
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
652022
Entrance detection from street-level imagery
J Liu, V Parameswaran, T Korah, V Hedau, R Grzeszczuk, Y Liu
US Patent 9,235,775, 2016
532016
Location-aided recognition
V Hedau, S Sinha, CL Zitnick, R Szeliski
US Patent 9,152,882, 2015
512015
Matching images under unstable segmentations
V Hedau, H Arora, N Ahuja
2008 IEEE Conference on Computer Vision and Pattern Recognition, 1-8, 2008
482008
3D city modeling from street-level data for augmented reality applications
T Pylvänäinen, J Berclaz, T Korah, V Hedau, M Aanjaneya, R Grzeszczuk
2012 Second International Conference on 3D Imaging, Modeling, Processing …, 2012
372012
Action energy images for reliable human action recognition
VH Chandrashekhar, KS Venkatesh
Proceedings of the Asian Symposium on Information Display (ASID’06), 484-487, 2006
332006
Inserting objects into content
K Karsch, VC Hedau, DA Forsyth, D Hoiem
US Patent 9,330,500, 2016
282016
Antnets: Mobile convolutional neural networks for resource efficient image classification
Y Xiong, HJ Kim, V Hedau
arXiv preprint arXiv:1904.03775, 2019
252019
Enhancing fairness in face detection in computer vision systems by demographic bias mitigation
Y Yang, A Gupta, J Feng, P Singhal, V Yadav, Y Wu, P Natarajan, ...
Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 813-822, 2022
182022
Asd-transformer: Efficient active speaker detection using self and multimodal transformers
G Datta, T Etchart, V Yadav, V Hedau, P Natarajan, SF Chang
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
102022
Entrance detection from street-view images
J Liu, T Korah, V Hedau, V Parameswaran, R Grzeszczuk, Y Liu
IEEE International Conference on Computer Vision and Pattern Recognition …, 2014
62014
A memory efficient discriminative approach for location aided recognition
V Hedau, SN Sinha, CL Zitnick, R Szeliski
Computer Vision–ECCV 2012. Workshops and Demonstrations: Florence, Italy …, 2012
62012
Entrance detection from street-level imagery
J Liu, V Parameswaran, T Korah, V Hedau, R Grzeszczuk, Y Liu
US Patent 10,289,911, 2019
42019
Entrance detection from street-level imagery
J Liu, V Parameswaran, T Korah, V Hedau, R Grzeszczuk, Y Liu
US Patent 9,798,931, 2017
42017
Few-Shot Gaze Estimation with Model Offset Predictors
J Ma, X Zhang, Y Wu, V Hedau, SF Chang
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
22022
3D spatial layout and geometric constraints for scene understanding
VC Hedau
University of Illinois at Urbana-Champaign, 2011
22011
The system can't perform the operation now. Try again later.
Articles 1–20