VIJAY KUMAR B G

I am a Senior Researcher at NEC Laboratories, America. Before joining NEC, I was a Research Scientist at PARC and prior to that I was a Research Fellow at the Australian Centre for Robotic Vision working with Prof. Ian Reid and Dr. Gustavo Carneiro. Before joining ACRV, I was a Researcher at the Advanced Research Group, Samsung Research. My research interests are in the areas of machine learning and computer vision with current focus on LLM Agents, Multimodal Large Language Models, Vision-Language Understanding, Self-supervised Representation Learning. I completed my Ph.D. in Computer science from Queen Mary University of London under Prof. Ioannis Patras. I received my MS in Electrical Engineering from IIT Madras. Google Scholar

Publications

LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning

S P Sharan, Francesco Pittaluga, Vijay Kumar B G, Manmohan Chandraker

Arxiv 2023

[PDF], [Webpage],[link]

Self-Training Large Language Models for Improved Visual Program Synthesis

With Visual Reinforcement

Zaid Khan, Vijay Kumar B G, Samuel Schulter, Manmohan Chandraker, Yun Fu

IEEE Computer Vision and Pattern Recognition  (CVPR 2024)  [Accepted]

[Coming soon]

Generating Enhanced Negatives for Training Language-Based Object Detectors

Shiyu Zhao, Long Zhao, Vijay Kumar B.G, Yumin Suh, Dimitris Metaxas, Manmohan Chandraker, Samuel Schulter


IEEE Computer Vision and Pattern Recognition  (CVPR 2024)  [Accepted]

[PDF], [link]

Taming Self-Training for Open-Vocabulary Object Detection

Shiyu Zhao, Samuel Schulter, Long Zhao, Zhixing Zhang, Vijay Kumar B.G, Yumin Suh, Manmohan Chandraker, Dimitris Metaxas

IEEE Computer Vision and Pattern Recognition  (CVPR 2024)  [Accepted]

[PDF], [Webpage],[link]

Exploring Question Decomposition for Zero-shot VQA

Zaid Khan, Vijay Kumar B G, Samuel Schulter, Manmohan Chandraker, Yun Fu

Neural Information Processing Systems (NeurIPS 2023)

[PDF], [Webpage],[link]

DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning

Wenxuan Bao, Francesco Pittaluga, Vijay Kumar B G, Vincent Bindschaedler

Neural Information Processing Systems (NeurIPS 2023)

[PDF], [Webpage],[link]

OmniLabel: A Challenging Benchmark for Language-Based Object Detection

Samuel Schulter, Vijay Kumar B G, Yumin Suh, Konstantinos M. Dafnis, Zhixing Zhang, Shiyu Zhao, Dimitris Metaxas

International Conference on Computer Vision (ICCV 2023)

[PDF], [Webpage],[Workshop],[Leaderboard]

Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks?A: Self-Train on Unlabeled Images!

Zaid Khan, Vijay Kumar B G, Samuel Schulter, Xiang Yu, Yun Fu,  Manmohan Chandraker

IEEE Computer Vision and Pattern Recognition  (CVPR 2023

[PDF], [link]

Single-Stream Multi-Level Alignment for Vision Language Pretraining

Zaid Khan, Vijay Kumar B G, Xiang Yu, Samuel Schulter, Manmohan Chandraker, Yun Fu

European Conference on Computer Vision (ECCV 2022

[PDF], [Webpage], [link],[Bibtex]

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Shiyu Zhao, Zhixing Zhang, Samuel Schulter, Long Zhao, Vijay Kumar B.G, Anastasis Stathopoulos, Manmohan Chandraker, Dimitris Metaxas

European Conference on Computer Vision (ECCV 2022)

[PDF], [Webpage], [link],[Bibtex]

STRIVE: Scene Text Replacement In Videos

Vijay Kumar B G, Jeyasri Subramanian, Varnith Chordia, Eugene Bart, Shaobo Fang, Kelly Guan, Raja Bala

IEEE International Conference on Computer Vision (ICCV 2021

[PDF], [Webpage], [link],[Bibtex]

Large Scale Multimodal Classification Using an Ensemble of Transformer Models and Co-Attention

Varnith Chordia , Vijay Kumar B G

SIGIR E.Comm Workshop (2020

[PDF], [link], [Bibtex]

Deep Retinal Image Segmentation with Regularization Under Geometric Priors

Venkateswararao Cherukuri, Vijay Kumar B G, Raja Bala,   Vishal Monga

IEEE Transactions on Image Processing (TIP 2019

[PDF], [link], [Bibtex]

A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning

Thanh-Toan Do, Toan Tran, Ian Reid, Vijay Kumar, Tuan Hoang, Gustavo Carneiro

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2019

[PDF], [link], [Bibtex]

Multi-Scale Regularized Deep Network for Retinal Vessel Segmentation

Venkateswararao Cherukuri, Vijay Kumar B G, Raja Bala, Vishal   Monga

IEEE International Conference on Image Processing (ICIP 2019

[link], [Bibtex]

Multi-modal Cycle-consistent Generalized Zero-Shot Learning

Rafael Felix, Vijay Kumar B G, Ian Reid and Gustavo Carneiro

European Conference on Computer Vision (ECCV 2018)

[PDF], [code], [link], [Bibtex]

Bayesian Semantic Instance Segmentation in Open Set World

Trung Pham, Vijay Kumar B G, Thanh-Toan Do, Gustavo Carneiro, and Ian Reid

European Conference on Computer Vision (ECCV 2018)

[PDF], [link], [Bibtex]

Semantic Segmentation from Limited Training Data

Anton Milan, Trung Pham, Vijay Kumar B G et. al.

IEEE International Conference on Robotics and Automation (ICRA 2018)

[PDF], [link], [Video], [Bibtex]

Cartman: The low-cost Cartesian Manipulator that won the Amazon Robotics Challenge

D Morrison et. al.

IEEE International Conference on Robotics and Automation (ICRA 2018)

[PDF], [link], [Video], [Bibtex], [BBC][MIT Tech Review], [IEEE Spectrum], [Team]

Smart Mining for Deep Metric Learning

Vijay Kumar B G*, Ben Harwood*, Gustavo Carneiro, Ian Reid, and Tom Drummond

IEEE International Conference on Computer Vision (ICCV 2017),

[PDF], [link], [Bibtex]

DeepSetNet: Predicting Sets with Deep Neural Networks 

Seyed Hamid Rezatofighi, Vijay Kumar B G, Anton Milan, Ehsan Abbasnejad, Antony Dick, Ian Reid

IEEE International Conference on Computer Vision (ICCV 2017), (Spotlight, Acceptance rate < 5%),

[PDF], [link], [Bibtex], [Demo]

Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue

Ravi Garg, Vijay Kumar B G, Gustavo Carneiro, and Ian Reid,

European Conference on Computer Vision (ECCV 2016)

[PDF], [link], [Bibtex],[videos],[code]

Learning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions

Vijay Kumar B G, Gustavo Carneiro, and Ian Reid

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2016) (Spotlight, Acceptance rate < 10%)

[PDF], [link], [Bibtex],[videos], [models]

Supervised Dictionary Learning for Action Localization

Vijay Kumar B G and Ioannis Patras

IEEE International Conference on Automatic Face and Gesture Recognition (FG 2013) (oral, Acceptance rate:12%)

[PDF], [link], [Bibtex],[videos]

Learning Codebook Weights for Action Detection

Vijay Kumar B G and Ioannis Patras

International Workshop on Large-Scale Video Search and Mining (CVPRW 2012

[PDF], [link], [Bibtex]

Max-Margin Non-Negative Matrix Factorization

Vijay Kumar B G, Irene Kotsia and Ioannis Patras

Image and Vision Computing, Elsevier (IVC 2012)

[PDF], [link], [Bibtex]

Max-Margin Semi-NMF

Vijay Kumar B G, Irene Kotsia and Ioannis Patras

British Machine Vision Conference (BMVC 2011)

[PDF], [link], [Bibtex]

A Discriminative Voting Scheme for Object Detection using Hough Forests

Vijay Kumar B G and Ioannis Patras

British Machine Vision Conference (BMVC 2010)

[PDF],[Bibtex]

Computationally Efficient Algorithm for Face Super resolution using (2D)2-PCA based Prior

Vijay Kumar B G and R Aravind

IET Image Processing, 2010

[link],[Bibtex]

A 2D Approach for Super resolution

Vijay Kumar B G and R Aravind

National Conference on Communications (NCC 2009)

[PDF],[Bibtex]

A 2D Model for Face Super resolution

Vijay Kumar B G and R Aravind

International Conference on Pattern Recognition (ICPR 2008)

[link] [Bibtex]

Face Hallucination Using OLPP and Kernel Ridge Regression

Vijay Kumar B G and R Aravind

IEEE International Conference on Image Processing (ICIP 2008)

[link][Bibtex]

 

 

Copyright © 2012 Vijay. All Rights Reserved.