Vijay Kumar, B G

12 publications

ICCV 2025 DWIM: Towards Tool-Aware Visual Reasoning via Discrepancy-Aware Workflow Generation & Instruct-Masking Tuning Fucai Ke, B G Vijay Kumar, Xingjian Leng, Zhixi Cai, Zaid Khan, Weiqing Wang, Pari Delir Haghighi, Hamid Rezatofighi, Manmohan Chandraker

CVPR 2024 Generating Enhanced Negatives for Training Language-Based Object Detectors Shiyu Zhao, Long Zhao, B G Vijay Kumar, Yumin Suh, Dimitris N. Metaxas, Manmohan Chandraker, Samuel Schulter

CVPR 2024 Taming Self-Training for Open-Vocabulary Object Detection Shiyu Zhao, Samuel Schulter, Long Zhao, Zhixing Zhang, B G Vijay Kumar, Yumin Suh, Manmohan Chandraker, Dimitris N. Metaxas

NeurIPS 2023 DP-Mix: Mixup-Based Data Augmentation for Differentially Private Learning Wenxuan Bao, Francesco Pittaluga, B G Vijay Kumar, Vincent Bindschaedler

NeurIPS 2023 Exploring Question Decomposition for Zero-Shot VQA Zaid Khan, B G Vijay Kumar, Samuel Schulter, Manmohan Chandraker, Yun Fu

ICCV 2023 OmniLabel: A Challenging Benchmark for Language-Based Object Detection Samuel Schulter, B G Vijay Kumar, Yumin Suh, Konstantinos M. Dafnis, Zhixing Zhang, Shiyu Zhao, Dimitris Metaxas

ECCV 2022 Exploiting Unlabeled Data with Vision and Language Models for Object Detection Shiyu Zhao, Zhixing Zhang, Samuel Schulter, Long Zhao, B G Vijay Kumar, Anastasis Stathopoulos, Manmohan Chandraker, Dimitris N. Metaxas

ECCV 2022 Single-Stream Multi-Level Alignment for Vision-Language Pretraining Zaid Khan, B G Vijay Kumar, Xiang Yu, Samuel Schulter, Manmohan Chandraker, Yun Fu

ICCV 2021 STRIVE: Scene Text Replacement in Videos B G Vijay Kumar, Jeyasri Subramanian, Varnith Chordia, Eugene Bart, Shaobo Fang, Kelly Guan, Raja Bala

ICCV 2017 DeepSetNet: Predicting Sets with Deep Neural Networks S. Hamid Rezatofighi, B G Vijay Kumar, Anton Milan, Ehsan Abbasnejad, Anthony Dick, Ian Reid

ICCV 2017 Smart Mining for Deep Metric Learning Ben Harwood, B G Vijay Kumar, Gustavo Carneiro, Ian Reid, Tom Drummond

CVPR 2016 Learning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions B G Vijay Kumar, Gustavo Carneiro, Ian Reid