V
Vinay Kaushik
Researcher at Indian Institute of Technology Delhi
Publications - 19
Citations - 70
Vinay Kaushik is an academic researcher from Indian Institute of Technology Delhi. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 3, co-authored 13 publications receiving 35 citations. Previous affiliations of Vinay Kaushik include Indian Institutes of Technology.
Papers
More filters
Proceedings ArticleDOI
VisDrone-MOT2019: The Vision Meets Drone Multiple Object Tracking Challenge Results
Longyin Wen,Yue Zhang,Liefeng Bo,Hailin Shi,Rui Zhu,Ajit Jadhav,Bing Dong,Brejesh Lall,Chang Liu,Chunhui Zhang,Dong Wang,Pengfei Zhu,Feng Ni,Filiz Bunyak,Gaoang Wang,Guizhong Liu,Guna Seetharaman,Guorong Li,Håkan Ardö,Haotian Zhang,Hongyang Yu,Huchuan Lu,Dawei Du,Jenq-Neng Hwang,Jiatong Mu,Jinrong Hu,Kannappan Palaniappan,Long Chen,Lu Ding,Martin Lauer,Mikael Nilsson,Noor M. Al-Shakarji,Prerana Mukherjee,Xiao Bian,Qingming Huang,Robert Laganiere,Shuhao Chen,Siyang Pan,Vinay Kaushik,Wei Shi,Wei Tian,Weiqiang Li,Xin Chen,Xinyu Zhang,Haibin Ling,Yanting Zhang,Yanyun Zhao,Yong Wang,Yuduo Song,Yuehan Yao,Zhaotang Chen,Zhenyu Xu,Zhibin Xiao,Zhihang Tong,Zhipeng Luo,Qinghua Hu,Zhuojin Sun,Jiayu Zheng,Tao Peng,Xinyao Wang +59 more
TL;DR: The challenge results show that MOT on drones is far from being solved, and it is believed the challenge can largely boost the research and development in MOT on drone platforms.
Proceedings ArticleDOI
Aerial Multi-Object Tracking by Detection Using Deep Association Networks
TL;DR: A model for detection of objects in drone images using the VisDrone2019 DET dataset, using the RetinaNet model as a base, and explicitly model the channel interdependencies by using “Squeeze-and-Excitation” (SE) blocks that adaptively recalibrates channel-wise feature responses.
Proceedings ArticleDOI
Nrityantar: Pose oblivious Indian classical dance sequence classification system
TL;DR: An exhaustive empirical evaluation of state-of-the-art deep network based methods for dance classification on ICD dataset helps in better establishing the spatio-temporal dependencies.
Journal ArticleDOI
ADAADepth: Adapting Data Augmentation and Attention for Self-Supervised Monocular Depth Estimation
TL;DR: ADAA as discussed by the authors proposes a relational self-attention module that learns rich contextual features and further enhances depth results, achieving state-of-the-art results for monocular depth estimation on the standard KITTI driving dataset.
Journal Article
Study of behavioural and physiological changes of crossbred cows under different shelter management practices
TL;DR: The study indicated that thatch roof and sand bedding in hot seasons and straw bedded in winter proved to be the most comfortable for crossbred cows in northern India.