no code implementations • 15 Jan 2024 • Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki
This paper addresses motion forecasting in multi-agent environments, pivotal for ensuring safety of autonomous vehicles.
1 code implementation • 28 Jun 2022 • Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki
Self-supervised learning (SSL) is an emerging technique that has been successfully employed to train convolutional neural networks (CNNs) and graph neural networks (GNNs) for more transferable, generalizable, and robust representation learning.
Ranked #59 on Motion Forecasting on Argoverse CVPR 2020
1 code implementation • 22 Jan 2022 • Prarthana Bhattacharyya, Chenge Li, Xiaonan Zhao, István Fehérvári, Jason Sun
For few-shot image classification we train SSL-ViTs without any supervision, on external data, and use this trained embedder to adapt quickly to novel classes with limited number of labels.
no code implementations • 10 Dec 2021 • Prarthana Bhattacharyya, Yanlei Gu, Jiali Bao, Xu Liu, Shunsuke Kamijo
The driving behavior at urban intersections is very complex.
1 code implementation • 7 Jan 2021 • Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki
In this paper, we propose two variants of self-attention for contextual modeling in 3D object detection by augmenting convolutional features with self-attention features.
Ranked #1 on 3D Object Detection on KITTI Cyclists Hard
2 code implementations • 20 Aug 2020 • Prarthana Bhattacharyya, Krzysztof Czarnecki
We present Deformable PV-RCNN, a high-performing point-cloud based 3D object detector.
1 code implementation • 7 May 2019 • Erkan Baser, Venkateshwaran Balasubramanian, Prarthana Bhattacharyya, Krzysztof Czarnecki
Instead, we exploit the power of deep learning to formulate the data association problem as inference in a CNN.
Ranked #4 on 3D Multi-Object Tracking on KITTI