Picture for Sudhir Yarram

Sudhir Yarram

Forecasting Future Videos from Novel Views via Disentangled 3D Scene Representation

Add code
Jul 31, 2024
Viaarxiv icon

Deformable VisTR: Spatio temporal deformable attention for video instance segmentation

Add code
Mar 12, 2022
Figure 1 for Deformable VisTR: Spatio temporal deformable attention for video instance segmentation
Figure 2 for Deformable VisTR: Spatio temporal deformable attention for video instance segmentation
Figure 3 for Deformable VisTR: Spatio temporal deformable attention for video instance segmentation
Figure 4 for Deformable VisTR: Spatio temporal deformable attention for video instance segmentation
Viaarxiv icon

Efficient Video Instance Segmentation via Tracklet Query and Proposal

Add code
Mar 03, 2022
Figure 1 for Efficient Video Instance Segmentation via Tracklet Query and Proposal
Figure 2 for Efficient Video Instance Segmentation via Tracklet Query and Proposal
Figure 3 for Efficient Video Instance Segmentation via Tracklet Query and Proposal
Figure 4 for Efficient Video Instance Segmentation via Tracklet Query and Proposal
Viaarxiv icon

City-Scale Road Audit System using Deep Learning

Add code
Nov 26, 2018
Figure 1 for City-Scale Road Audit System using Deep Learning
Figure 2 for City-Scale Road Audit System using Deep Learning
Figure 3 for City-Scale Road Audit System using Deep Learning
Figure 4 for City-Scale Road Audit System using Deep Learning
Viaarxiv icon