no code implementations • 16 May 2024 • Vage Taamazyan, Alberto Dall'olio, Agastya Kalra
3D cameras have emerged as a critical source of information for applications in robotics and autonomous driving.
1 code implementation • ICCV 2021 • Agastya Kalra, Guy Stoppi, Bradley Brown, Rishav Agarwal, Achuta Kadambi
Rotation augmentations generally improve a model's invariance/equivariance to rotation - except in object detection.
no code implementations • CVPR 2020 • Agastya Kalra, Vage Taamazyan, Supreeth Krishna Rao, Kartik Venkataraman, Ramesh Raskar, Achuta Kadambi
Segmentation of transparent objects is a hard, open problem in computer vision.
1 code implementation • 9 Jan 2020 • Abdullah Rashwan, Rishav Agarwal, Agastya Kalra, Pascal Poupart
We present MatrixNets (xNets), a new deep architecture for object detection.
2 code implementations • 13 Aug 2019 • Abdullah Rashwan, Agastya Kalra, Pascal Poupart
We present Matrix Nets (xNets), a new deep architecture for object detection.
Ranked #108 on Object Detection on COCO test-dev
no code implementations • 16 Apr 2019 • Agastya Kalra, Ben Peterson
In just a few years, online dating has become the dominant way that young people meet to date, making the deceptively error-prone task of picking good dating profile photos vital to a generation's ability to form romantic connections.
no code implementations • NeurIPS 2018 • Agastya Kalra, Abdullah Rashwan, Wei-Shou Hsu, Pascal Poupart, Prashant Doshi, Georgios Trimponias
Sum-product networks have recently emerged as an attractive representation due to their dual view as a special type of deep neural network with clear semantics and a special type of probabilistic graphical model for which inference is always tractable.
1 code implementation • 19 Jan 2017 • Wilson Hsu, Agastya Kalra, Pascal Poupart
Sum-product networks have recently emerged as an attractive representation due to their dual view as a special type of deep neural network with clear semantics and a special type of probabilistic graphical model for which inference is always tractable.