1 code implementation • 12 Mar 2022 • Sudhir Yarram, Jialian Wu, Pan Ji, Yi Xu, Junsong Yuan
To improve the training efficiency, we propose Deformable VisTR, leveraging spatio-temporal deformable attention module that only attends to a small fixed set of key spatio-temporal sampling points around a reference point.
no code implementations • CVPR 2022 • Jialian Wu, Sudhir Yarram, Hui Liang, Tian Lan, Junsong Yuan, Jayan Eledath, Gerard Medioni
In addition, VisTR is not fully end-to-end learnable in multiple video clips as it requires a hand-crafted data association to link instance tracklets between successive clips.
1 code implementation • 26 Nov 2018 • Sudhir Yarram, Girish Varma, C. V. Jawahar
Road networks in cities are massive and is a critical component of mobility.