[go: up one dir, main page]

Follow
Vijay Kumar B G
Vijay Kumar B G
Senior Researcher at NEC Labs, America
Verified email at nec-labs.com - Homepage
Title
Cited by
Cited by
Year
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
R Garg, I Vijay Kumar B G, Gustavo Carneiro, Reid
European Conference on Computer Vision, (ECCV 2016), 2016
20882016
Multi-modal cycle-consistent generalized zero-shot learning
R Felix, I Reid, G Carneiro
Proceedings of the European conference on computer vision (ECCV), 21-37, 2018
5072018
Smart mining for deep metric learning
VB Kumar, B Harwood, G Carneiro, I Reid, T Drummond
IEEE International Conference on Computer Vision, (ICCV 2017), 2017
466*2017
Learning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions
BG Vijay Kumar, G Carneiro, I Reid
IEEE Conference on Computer Vision and Pattern Recognition, (CVPR 2016), 2015
419*2015
Cartman: The low-cost cartesian manipulator that won the amazon robotics challenge
D Morrison, AW Tow, M Mctaggart, R Smith, N Kelly-Boxall, ...
2018 IEEE international conference on robotics and automation (ICRA), 7757-7764, 2018
2012018
Exploiting unlabeled data with vision and language models for object detection
S Zhao, Z Zhang, S Schulter, L Zhao, BG Vijay Kumar, A Stathopoulos, ...
European conference on computer vision, 159-175, 2022
1452022
A theoretically sound upper bound on the triplet loss for improving the efficiency of deep distance metric learning
TT Do, T Tran, I Reid, V Kumar, T Hoang, G Carneiro
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019
852019
Deep retinal image segmentation with regularization under geometric priors
V Cherukuri, VK Bg, R Bala, V Monga
IEEE Transactions on Image Processing 29, 2552-2567, 2019
782019
Llm-assist: Enhancing closed-loop planning with language-based reasoning
SP Sharan, F Pittaluga, M Chandraker
arXiv preprint arXiv:2401.00125, 2023
732023
Semantic segmentation from limited training data
A Milan, T Pham, K Vijay, D Morrison, AW Tow, L Liu, J Erskine, ...
2018 IEEE international conference on robotics and automation (ICRA), 1908-1915, 2018
682018
DeepSetNet: Predicting Sets with Deep Neural Networks
SH Rezatofighi, V Kumar BG, A Milan, E Abbasnejad, A Dick, I Reid
IEEE International Conference on Computer Vision (ICCV 2017), 2016
65*2016
Bayesian semantic instance segmentation in open set world
T Pham, TT Do, G Carneiro, I Reid
Proceedings of the European Conference on Computer Vision (ECCV), 3-18, 2018
462018
Q: How to specialize large vision-language models to data-scarce vqa tasks? a: Self-train on unlabeled images!
Z Khan, VK BG, S Schulter, X Yu, Y Fu, M Chandraker
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
282023
Single-stream multi-level alignment for vision-language pretraining
Z Khan, BG Vijay Kumar, X Yu, S Schulter, M Chandraker, Y Fu
European Conference on Computer Vision, 735-751, 2022
272022
Computationally efficient algorithm for face super-resolution using (2D)2-PCA based prior
BG Vijay Kumar, R Aravind
IET image processing 4 (2), 61-69, 2010
262010
Max-margin non-negative matrix factorization
BGV Kumar, I Kotsia, I Patras
Image and Vision Computing 30 (4-5), 279-291, 2012
252012
Face hallucination using OLPP and kernel ridge regression
BGV Kumar, R Aravind
2008 15th IEEE International Conference on Image Processing, 353-356, 2008
232008
Taming self-training for open-vocabulary object detection
S Zhao, S Schulter, L Zhao, Z Zhang, Y Suh, M Chandraker, DN Metaxas
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024
222024
Exploring question decomposition for zero-shot vqa
Z Khan, VK BG, S Schulter, M Chandraker, Y Fu
Advances in Neural Information Processing Systems 36, 56615-56627, 2023
222023
Dp-mix: mixup-based data augmentation for differentially private learning
W Bao, F Pittaluga, VK BG, V Bindschaedler
Advances in Neural Information Processing Systems 36, 12154-12170, 2023
212023
The system can't perform the operation now. Try again later.
Articles 1–20