no code implementations • 12 May 2023 • Xinyu Gong, Sreyas Mohan, Naina Dhingra, Jean-Charles Bazin, Yilei Li, Zhangyang Wang, Rakesh Ranjan
In this paper, we study a novel problem in egocentric action recognition, which we term as "Multimodal Generalization" (MMG).
no code implementations • CVPR 2023 • Xinyu Gong, Sreyas Mohan, Naina Dhingra, Jean-Charles Bazin, Yilei Li, Zhangyang Wang, Rakesh Ranjan
In this paper, we study a novel problem in egocentric action recognition, which we term as "Multimodal Generalization" (MMG).
no code implementations • 7 Feb 2022 • Naina Dhingra
The significance of using a transformer encoder for HPE is studied.
1 code implementation • 7 Feb 2022 • Naina Dhingra
This paper presents a lightweight network for head pose estimation (HPE) task.
no code implementations • 11 Sep 2021 • Naina Dhingra, George Chogovadze, Andreas Kunz
We present Border-SegGCN, a novel architecture to improve semantic segmentation by refining the border outline using graph convolutional networks (GCN).
no code implementations • 11 Sep 2021 • Naina Dhingra, Florian Ritter, Andreas Kunz
Scene graph generation (SGG) aims to identify the objects and their relationships.
no code implementations • 4 Jan 2020 • Naina Dhingra, Andreas Kunz
Based on the stacked multiple attention blocks, we build a 3D network which generates different features at each attention block.